© 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. 103593
    Prev
    Next
    INDEX
    Explanations

    Assistant and CNN

    np_max-act · gemini-2.0-flash

    Tokens that occur inside assistant-generated responses (i.e., the "assistant" speaker/response segments).

    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_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
    ongyang
    -0.07
     ø
    -0.07
    .Designer
    -0.06
    >[↵
    -0.06
     ##↵
    -0.06
    IND
    -0.06
     catholic
    -0.06
     {
↵
    -0.06
     açıklam
    -0.06
     }↵↵↵↵
    -0.06
    POSITIVE LOGITS
     masse
    0.07
    ～～
    0.06
     또
    0.06
    ather
    0.06
    InOut
    0.06
    _HANDLER
    0.06
    ildren
    0.06
     également
    0.06
    νομ
    0.06
    @SuppressWarnings
    0.06
    Activations Density 0.131%

    No Known Activations