© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 36901
    Prev
    Next
    INDEX
    Explanations

    Programming answers

    np_max-act · gemini-2.0-flash

    discussions related to coding and programming errors in software development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on the English “answer” prose (the explanatory sentences of a response) rather than on the code or question text.

    oai_token-act-pair · o4-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
     enfermed
    -0.07
     developmental
    -0.07
    BackPressed
    -0.07
    phetamine
    -0.07
     extensive
    -0.07
     Gö
    -0.07
     assistance
    -0.06
     urinary
    -0.06
    '\
    -0.06
     Extraction
    -0.06
    POSITIVE LOGITS
    .star
    0.07
     tantra
    0.06
    _DISCONNECT
    0.06
    wargs
    0.06
    _LL
    0.06
     바라
    0.06
     وم
    0.06
    tile
    0.06
     lệ
    0.06
    agascar
    0.06
    Activations Density 0.096%

    No Known Activations