© 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 (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 57682
    Prev
    Next
    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash

    tokens expressing attempts to contact, reach, or communicate with someone (forms of outreach/response).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
     صورت
    -0.07
     тщ
    -0.07
    ایل
    -0.07
     trip
    -0.06
     Tell
    -0.06
    措
    -0.06
     igual
    -0.06
    當
    -0.06
     dial
    -0.06
    иться
    -0.06
    POSITIVE LOGITS
    .cod
    0.06
    _TD
    0.06
     qed
    0.06
    alice
    0.06
    gregate
    0.06
     ISP
    0.06
    .primary
    0.06
    issuer
    0.06
    .ent
    0.06
    .remaining
    0.06
    Activations Density 0.595%

    No Known Activations