Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93225
    Prev
    Next
    INDEX
    Explanations

    /

    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
     müssen
    -0.07
     sav
    -0.06
    tering
    -0.06
    jezd
    -0.06
     indirectly
    -0.06
     bức
    -0.06
     Herman
    -0.06
    existence
    -0.06
    Various
    -0.06
    .data
    -0.06
    POSITIVE LOGITS
    .tie
    0.07
    _REUSE
    0.06
    -Sep
    0.06
    roleId
    0.06
    -city
    0.06
    /self
    0.06
    σιμοποι
    0.06
     //=
    0.06
     thang
    0.06
    raf
    0.06
    Activations Density 0.002%

    No Known Activations