© 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. 104779
    Prev
    Next
    INDEX
    Explanations

    mathrm

    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
     NE
    -0.07
    ५
    -0.07
     gu
    -0.07
    ۲۷
    -0.07
     AH
    -0.07
    uh
    -0.07
    /
    -0.06
    7
    -0.06
     hh
    -0.06
    ۲۳
    -0.06
    POSITIVE LOGITS
    mathrm
    0.09
    ステム
    0.07
    .Dis
    0.07
    θεια
    0.07
    існо
    0.07
    ßen
    0.07
    .press
    0.07
    getData
    0.06
    _PERMISSION
    0.06
     offsetof
    0.06
    Activations Density 0.006%

    No Known Activations