© 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. 7045
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron detects discourse markers and verbs that introduce research aims, hypotheses, or conclusions (e.g. “suggesting,” “hypothesize,” “determine,” “will”).

    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
    SAVE
    -0.07
    _TRANSACTION
    -0.07
    _texts
    -0.07
     naked
    -0.07
    bish
    -0.06
    reat
    -0.06
    ainment
    -0.06
     spotted
    -0.06
    anes
    -0.06
     peaks
    -0.06
    POSITIVE LOGITS
    =pd
    0.07
     маз
    0.06
     configur
    0.06
    \Config
    0.06
     Tomas
    0.06
    executor
    0.06
    停
    0.06
    าษฎ
    0.06
    ネット
    0.06
    polator
    0.06
    Activations Density 0.037%

    No Known Activations