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. 73080
    Prev
    Next
    INDEX
    Explanations

    file permissions

    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
    aviour
    -0.07
    isicing
    -0.06
     pursued
    -0.06
    rends
    -0.06
    living
    -0.06
    ervals
    -0.06
    ,并
    -0.06
    heard
    -0.06
    fout
    -0.06
     Roman
    -0.06
    POSITIVE LOGITS
    로그
    0.07
     wäre
    0.07
     firmy
    0.07
    ircon
    0.07
     TOM
    0.07
     pollut
    0.06
     Díky
    0.06
    Perfil
    0.06
     엔
    0.06
    )(__
    0.06
    Activations Density 0.003%

    No Known Activations