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. 15-RESID-POST-AA
    6. 88900
    Prev
    Next
    INDEX
    Explanations

    /

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _vectors
    -0.07
     Ris
    -0.07
    getToken
    -0.06
    _cred
    -0.06
     Drops
    -0.06
    Routing
    -0.06
    ziej
    -0.06
     Rx
    -0.06
    érica
    -0.06
    ,mid
    -0.06
    POSITIVE LOGITS
    ovatel
    0.07
    .GetComponent
    0.06
    ्म
    0.06
     asserted
    0.06
    title
    0.06
    学
    0.06
    kan
    0.06
     supplement
    0.06
     BMW
    0.06
     Joseph
    0.06
    Activations Density 0.000%

    No Known Activations