© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 77844
    Prev
    Next
    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash

    the first content word at the start of a new passage or paragraph

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fold
    -0.06
     rigged
    -0.06
     Pert
    -0.06
    /chart
    -0.06
    (domain
    -0.06
     และ
    -0.06
     Vander
    -0.06
    -element
    -0.06
    ingga
    -0.06
     dest
    -0.06
    POSITIVE LOGITS
    ód
    0.07
    _Out
    0.07
    antor
    0.06
    DBNull
    0.06
     Munich
    0.06
    $view
    0.06
    _GENERAL
    0.06
     никогда
    0.06
    .requires
    0.06
    .ExecuteNonQuery
    0.06
    Activations Density 0.447%

    No Known Activations