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

    Neuronpedia

    APICircuit 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. 93238
    Prev
    Next
    INDEX
    Explanations

    careful

    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
     Channels
    -0.08
     reserves
    -0.07
    elo
    -0.06
     får
    -0.06
    收录
    -0.06
    ايت
    -0.06
    .middleware
    -0.06
    地址
    -0.06
    iku
    -0.06
    聽
    -0.06
    POSITIVE LOGITS
     narrative
    0.07
     saf
    0.06
     CrossAxisAlignment
    0.06
    grav
    0.06
    levelname
    0.06
    Hon
    0.06
     Huntington
    0.06
    >--
    0.06
    (mod
    0.06
    (LocalDate
    0.06
    Activations Density 0.015%

    No Known Activations