© 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. 7-RESID-POST-AA
    11. 128147
    Prev
    Next
    INDEX
    Explanations

    Web page snippets

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    155
    -0.06
     financier
    -0.06
     handlers
    -0.06
    esters
    -0.06
    рана
    -0.06
    156
    -0.05
     Shame
    -0.05
     installs
    -0.05
    },{
    -0.05
    쳤다
    -0.05
    POSITIVE LOGITS
     моб
    0.07
    KR
    0.07
     actions
    0.07
    功能
    0.07
    'я
    0.06
    .DecimalField
    0.06
    <Action
    0.06
    ;:;:;:;:
    0.06
    iễn
    0.06
     bundle
    0.06
    Activations Density 0.141%

    No Known Activations