© 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. 5546
    Prev
    Next
    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash

    This neuron detects conversation or sequence boundary tokens (end-of-turn / end-of-text markers) indicating segment breaks in the chat.

    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
    _ball
    -0.06
    wd
    -0.06
     diplomatic
    -0.06
    LIST
    -0.06
    Prefix
    -0.06
    (Query
    -0.06
    _actions
    -0.06
    _Details
    -0.06
     scorn
    -0.06
     abandoned
    -0.06
    POSITIVE LOGITS
     करव
    0.07
    슬
    0.06
     sesame
    0.06
     sparkle
    0.06
     doubly
    0.06
     использ
    0.06
    ест
    0.06
    aux
    0.06
    ้าพ
    0.06
     fine
    0.06
    Activations Density 0.096%

    No Known Activations