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. 11-RESID-POST-AA
    6. 20258
    Prev
    Next
    INDEX
    Explanations

    workshop

    np_max-act · gemini-2.0-flash

    terms and concepts related to health and medical research.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uç
    -0.08
    ServiceProvider
    -0.06
    Merge
    -0.06
    spent
    -0.06
    Both
    -0.06
    ullen
    -0.06
    rying
    -0.06
    erguson
    -0.06
    ullet
    -0.06
    ど
    -0.06
    POSITIVE LOGITS
    ('',
    0.07
     ramp
    0.07
     webpage
    0.07
     exercitation
    0.07
     Are
    0.07
    译
    0.07
     HAL
    0.07
     burdens
    0.07
     Hub
    0.06
    (delta
    0.06
    Activations Density 0.057%

    No Known Activations