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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RESID-POST-AA
    6. 123020
    Prev
    Next
    INDEX
    Explanations

    at

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -lnd
    -0.07
    amble
    -0.06
     mluv
    -0.06
     ZZ
    -0.06
    apos
    -0.06
    Uno
    -0.06
     sizeof
    -0.06
     '!
    -0.06
    **************
    -0.06
     uyg
    -0.06
    POSITIVE LOGITS
    ="";
    ↵
    0.07
     acl
    0.07
     humorous
    0.07
    "))
    ↵
    0.06
    __));↵
    0.06
     لكل
    0.06
    ;
    ↵
    0.06
     Gat
    0.06
    "];
    ↵
    0.06
    )}
    ↵
    0.06
    Activations Density 0.001%

    No Known Activations