© 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. 78229
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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
     monuments
    -0.07
     terminology
    -0.07
    83
    -0.06
     '.',
    -0.06
    服
    -0.06
    _Type
    -0.06
    SetBranchAddress
    -0.06
    background
    -0.06
    _orders
    -0.06
    uglify
    -0.06
    POSITIVE LOGITS
     глаз
    0.07
     scipy
    0.06
     İlk
    0.06
     قتل
    0.06
     самостоятель
    0.06
     boo
    0.06
     друж
    0.06
     如
    0.06
    lete
    0.06
    sembl
    0.06
    Activations Density 0.157%

    No Known Activations