© 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. 7-RESID-POST-AA
    11. 118924
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash

    whether the user is issuing a direct request/command (imperative prompt) asking the assistant to produce something.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    Accordion
    -0.07
    aul
    -0.07
     Sesso
    -0.07
    洪
    -0.06
     Leah
    -0.06
    foreground
    -0.06
    470
    -0.06
    bounding
    -0.06
    ponent
    -0.06
     pigeon
    -0.06
    POSITIVE LOGITS
     adopted
    0.06
    �
    0.06
    Implement
    0.06
    .fil
    0.06
    ';↵↵↵
    0.06
    -ip
    0.06
    -support
    0.06
    /product
    0.06
    ｍ
    0.06
    .scheme
    0.06
    Activations Density 0.080%

    No Known Activations