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. 19-RESID-POST-AA
    6. 83069
    Prev
    Next
    INDEX
    Explanations

    rol

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⠀⠀
    -0.07
    tplib
    -0.06
    :update
    -0.06
    éf
    -0.06
     {\↵
    -0.06
    >"+↵
    -0.06
    .Generated
    -0.06
    .Release
    -0.06
     fern
    -0.06
     enraged
    -0.06
    POSITIVE LOGITS
    jections
    0.07
    Ệ
    0.06
     prevailing
    0.06
    нит
    0.06
    atings
    0.06
    normalize
    0.06
    won
    0.06
     nikdy
    0.06
    (localStorage
    0.06
    LOS
    0.06
    Activations Density 0.006%

    No Known Activations