© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 52366
    Prev
    Next
    INDEX
    Explanations

    medical research

    np_max-act · gemini-2.0-flash

    topics related to genetic mutations and their effects on development and health.

    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
     Hollande
    -0.07
    Password
    -0.07
    _txt
    -0.07
    _timeout
    -0.07
    ulo
    -0.07
     Restrictions
    -0.06
    ,{
    -0.06
    ,t
    -0.06
     runway
    -0.06
    IOS
    -0.06
    POSITIVE LOGITS
     ổ
    0.06
    鼠
    0.06
     muddy
    0.06
    .observe
    0.06
     حم
    0.06
     которое
    0.06
    чила
    0.06
    _equals
    0.06
    >--}}↵
    0.06
     kosten
    0.05
    Activations Density 0.007%

    No Known Activations