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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 23-RESID-POST-AA
    6. 104850
    Prev
    Next
    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Certificate
    -0.06
    ुक
    -0.06
    _constraint
    -0.06
     BSON
    -0.06
    statistics
    -0.06
     Satisfaction
    -0.06
    lever
    -0.06
    departments
    -0.06
    Cargo
    -0.06
    .↵
    -0.06
    POSITIVE LOGITS
    _download
    0.06
     demons
    0.06
     trắng
    0.06
     Manus
    0.06
    (params
    0.06
     dysfunctional
    0.06
     centerX
    0.06
    .labelX
    0.05
     BUILD
    0.05
    .didReceiveMemoryWarning
    0.05
    Activations Density 0.007%

    No Known Activations