© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 105070
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .logout
    -0.07
    erland
    -0.07
     straw
    -0.06
    _macros
    -0.06
     accessible
    -0.06
    -by
    -0.06
    씀
    -0.06
     الذهاب
    -0.06
    UEL
    -0.06
    unwrap
    -0.06
    POSITIVE LOGITS
     nutritious
    0.07
     Oct
    0.06
    _STORE
    0.06
    _perc
    0.06
    .moves
    0.06
     thu
    0.06
     voice
    0.06
     BMP
    0.06
    ủng
    0.06
    ouve
    0.06
    Activations Density 0.017%

    No Known Activations