© 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. 3-RESID-POST-AA
    11. 123083
    Prev
    Next
    INDEX
    Explanations

    strict

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .root
    -0.07
    _buf
    -0.07
     concaten
    -0.06
     ';↵
    -0.06
     इसल
    -0.06
    _LINES
    -0.06
     produ
    -0.06
     bishops
    -0.06
    TMP
    -0.06
     souvenir
    -0.06
    POSITIVE LOGITS
    Lean
    0.15
    /latest
    0.15
     mileage
    0.12
    Laugh
    0.11
     Warwick
    0.11
    .*?)
    0.09
    lean
    0.08
     lord
    0.07
     Pediatric
    0.07
    alette
    0.06
    Activations Density 0.003%

    No Known Activations