© 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. 11-RESID-POST-AA
    11. 66240
    Prev
    Next
    INDEX
    Explanations

    -

    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
     유형
    -0.06
    //****************************************************************
    -0.06
    (ship
    -0.06
     yapım
    -0.06
     lighten
    -0.06
    och
    -0.06
     ########################################################################
    -0.06
    prd
    -0.06
     bracelet
    -0.06
    variables
    -0.06
    POSITIVE LOGITS
    -def
    0.07
    .Obj
    0.06
    -wh
    0.06
    plays
    0.06
    _bank
    0.06
    -task
    0.06
     nationwide
    0.06
    posing
    0.06
    predicted
    0.06
    ked
    0.06
    Activations Density 0.012%

    No Known Activations