© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109195
    Prev
    Next
    INDEX
    Explanations

    absolute

    np_max-act · gemini-2.0-flash

    chemical compounds with specified structural characteristics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects phrases describing the elucidation or determination of chemical structures and stereochemical configurations (e.g. “structures … were established,” “absolute configuration … was determined,” “relative stereochemistry”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Το
    -0.07
    ッカー
    -0.07
     mec
    -0.06
    Advanced
    -0.06
    .year
    -0.06
    .Count
    -0.06
    .contents
    -0.06
     nrows
    -0.06
    	column
    -0.06
     Enemy
    -0.06
    POSITIVE LOGITS
    腦
    0.07
    isser
    0.06
    .CR
    0.06
     ApplicationDbContext
    0.06
     gratuito
    0.06
    /disable
    0.06
     кон
    0.06
    fcc
    0.06
    Monster
    0.06
    остав
    0.06
    Activations Density 0.002%

    No Known Activations