© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 99147
    Prev
    Next
    INDEX
    Explanations

    romans

    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
    _pf
    -0.06
     Annotations
    -0.06
     Purch
    -0.06
    _SEP
    -0.06
     fulfillment
    -0.06
     giorn
    -0.06
     replication
    -0.06
     Pool
    -0.06
    .";
    -0.06
    _delay
    -0.06
    POSITIVE LOGITS
     Romans
    0.07
    那么
    0.07
     hate
    0.07
     الجز
    0.06
    Prev
    0.06
     Beatles
    0.06
    lator
    0.06
    طار
    0.06
    .log
    0.06
    Wrapped
    0.06
    Activations Density 0.003%

    No Known Activations