© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30092
    Prev
    Next
    INDEX
    Explanations

    quite

    np_max-act · gemini-2.0-flash

    The neuron responds to adverbs or small function words that intensify or qualify descriptions—e.g. “quite,” “very,” or “being” when used to strengthen an adjective.

    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
     able
    -0.07
    '&&
    -0.07
     IOException
    -0.06
    _POINTER
    -0.06
    Vals
    -0.06
     steel
    -0.06
     resizing
    -0.06
    _Normal
    -0.06
     written
    -0.06
     Able
    -0.06
    POSITIVE LOGITS
     onPress
    0.07
     아주
    0.07
    .Channel
    0.06
     more
    0.06
     khuôn
    0.06
     completamente
    0.06
    比較
    0.06
    =zeros
    0.06
     molto
    0.06
    compat
    0.06
    Activations Density 0.154%

    No Known Activations