© 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 (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 99841
    Prev
    Next
    INDEX
    Explanations

    for

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    舌
    -0.07
    τρα
    -0.06
    (DbContext
    -0.06
     şer
    -0.06
     نموده
    -0.06
    ilee
    -0.06
     excursion
    -0.06
     worden
    -0.06
    шила
    -0.06
     nhằm
    -0.06
    POSITIVE LOGITS
    ,#
    0.07
     accounted
    0.07
    |M
    0.07
    |h
    0.06
    :"",
    0.06
    ضي
    0.06
     constituents
    0.06
    ,//
    0.06
     eyebrows
    0.06
    pire
    0.06
    Activations Density 0.010%

    No Known Activations