© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 75035
    Prev
    Next
    INDEX
    Explanations

    scientific/medical research

    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
     pity
    -0.07
     mods
    -0.06
    udy
    -0.06
     observed
    -0.06
     되었
    -0.06
     isp
    -0.06
     bets
    -0.06
    >x
    -0.06
    Copy
    -0.06
    Vy
    -0.06
    POSITIVE LOGITS
    .INTERNAL
    0.06
     необходим
    0.06
    _sprite
    0.06
    :param
    0.06
     mayoría
    0.06
     último
    0.06
     directives
    0.06
    *sizeof
    0.06
    capture
    0.06
     répond
    0.06
    Activations Density 0.184%

    No Known Activations