Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 39478
    Prev
    Next
    INDEX
    Explanations

    local

    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
     teasing
    -0.07
    řik
    -0.07
     manufacture
    -0.06
    rin
    -0.06
     süresi
    -0.06
     Cruiser
    -0.06
     garnered
    -0.06
     Razor
    -0.06
     rundown
    -0.06
     Vil
    -0.06
    POSITIVE LOGITS
     narratives
    0.07
    (dictionary
    0.07
    .',
    0.06
     issu
    0.06
    (dec
    0.06
    атив
    0.06
    choices
    0.06
     pratic
    0.06
     соврем
    0.06
    anything
    0.06
    Activations Density 0.003%

    No Known Activations