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. 36344
    Prev
    Next
    INDEX
    Explanations

    code strings

    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
    .tree
    -0.07
     sin
    -0.07
    speech
    -0.07
     walk
    -0.07
    -girl
    -0.06
    values
    -0.06
    _manual
    -0.06
    /src
    -0.06
     rode
    -0.06
     album
    -0.06
    POSITIVE LOGITS
     trang
    0.06
     isEmpty
    0.06
    erno
    0.06
    _ENSURE
    0.06
    .retrieve
    0.06
     UNIQUE
    0.06
     Cats
    0.06
     pinMode
    0.06
    _gshared
    0.06
    invite
    0.06
    Activations Density 0.007%

    No Known Activations