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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 60453
    Prev
    Next
    INDEX
    Explanations

    variable types in code

    np_max-act · gemini-2.0-flash
    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
    _detail
    -0.07
    ば
    -0.07
    BA
    -0.07
     Predict
    -0.06
    !<
    -0.06
    덕
    -0.06
     DE
    -0.06
     Majesty
    -0.06
     Electro
    -0.06
    .Pull
    -0.06
    POSITIVE LOGITS
     mailbox
    0.07
    Wildcard
    0.06
     '='
    0.06
    _floor
    0.06
    undred
    0.06
     viv
    0.06
     Pure
    0.06
     diving
    0.06
    Ten
    0.06
    ísto
    0.06
    Activations Density 0.019%

    No Known Activations