© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 18525
    Prev
    Next
    INDEX
    Explanations

    select

    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
    _idxs
    -0.07
     존재
    -0.06
     graphene
    -0.06
     occasionally
    -0.06
    _client
    -0.06
     bran
    -0.06
     commuting
    -0.06
    qrstuvwxyz
    -0.06
    _special
    -0.06
     left
    -0.06
    POSITIVE LOGITS
     Async
    0.07
    补
    0.06
    เภ
    0.06
    .Utc
    0.06
    ymology
    0.06
    İL
    0.06
     prz
    0.06
     Clothing
    0.06
    _Panel
    0.06
     Prescott
    0.06
    Activations Density 0.023%

    No Known Activations