© 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. 118983
    Prev
    Next
    INDEX
    Explanations

    exploits

    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
    onse
    -0.07
    uga
    -0.07
     yerleş
    -0.06
    parison
    -0.06
    _pressed
    -0.06
     конструкции
    -0.06
    Framework
    -0.06
    /ms
    -0.06
    Dies
    -0.06
    ани
    -0.06
    POSITIVE LOGITS
     paras
    0.07
     tel
    0.07
    林
    0.06
     ere
    0.06
    Avatar
    0.06
     λα
    0.06
    FILE
    0.06
    :<
    0.06
    '){
↵
    0.06
     memo
    0.06
    Activations Density 0.006%

    No Known Activations