© 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. 44755
    Prev
    Next
    INDEX
    Explanations

    code configuration files

    np_max-act · gemini-2.0-flash

    The neuron fires on the leading capitalized words at the start of comment or license‐header lines (e.g. “All,” “This,” “The,” “If,” “For”) in source‐code documentation blocks.

    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
    通信
    -0.07
    WebService
    -0.07
     isError
    -0.06
     крови
    -0.06
    extField
    -0.06
    139
    -0.06
    PARSE
    -0.06
     день
    -0.06
    titles
    -0.06
    crow
    -0.06
    POSITIVE LOGITS
    ём
    0.07
     Experiment
    0.06
    要
    0.06
    (cluster
    0.06
     처
    0.06
     Miche
    0.06
     Broncos
    0.06
     spite
    0.06
     ">"
    0.05
    Loc
    0.05
    Activations Density 0.034%

    No Known Activations