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. 100483
    Prev
    Next
    INDEX
    Explanations

    reactions, actions

    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
    _DEFINITION
    -0.07
     अद
    -0.06
    981
    -0.06
     MsgBox
    -0.06
    できる
    -0.06
     debugging
    -0.06
     kteří
    -0.06
    Package
    -0.06
    _Pos
    -0.06
    _EMP
    -0.06
    POSITIVE LOGITS
    .avatar
    0.07
    ómo
    0.07
     steroid
    0.07
    Creative
    0.06
    /response
    0.06
    chi
    0.06
     quantitative
    0.06
     spare
    0.06
     cardiovascular
    0.06
     galaxy
    0.06
    Activations Density 0.011%

    No Known Activations