© 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
    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. 78246
    Prev
    Next
    INDEX
    Explanations

    car culture

    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
     coli
    -0.07
    .ERR
    -0.06
     Minor
    -0.06
    ви
    -0.06
     싶
    -0.06
    เห
    -0.06
     �
    -0.06
     VH
    -0.06
    ']);
↵
    -0.06
    _nr
    -0.06
    POSITIVE LOGITS
     Acrobat
    0.07
     rtl
    0.06
     مثلا
    0.06
     projekt
    0.06
    <Location
    0.06
     vữ
    0.06
    ,↵↵
    0.05
     форм
    0.05
    __,
    0.05
    DISPLAY
    0.05
    Activations Density 0.122%

    No Known Activations