© 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. 11-RESID-POST-AA
    11. 7913
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    The neuron is maximally triggered by common English function words—especially high-frequency auxiliaries, conjunctions, and pronouns like “to,” “and,” “is,” “it,” “that,” etc.

    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
    Conditional
    -0.07
    ANDING
    -0.06
     thôn
    -0.06
    Called
    -0.06
    استان
    -0.06
     quarterback
    -0.06
    ...');↵
    -0.06
     해
    -0.06
     Sutton
    -0.06
    =add
    -0.06
    POSITIVE LOGITS
     cliffs
    0.07
     específ
    0.07
     tog
    0.07
    	double
    0.06
    [word
    0.06
    .El
    0.06
     ấn
    0.06
     productService
    0.06
     Descriptor
    0.06
     jur
    0.06
    Activations Density 0.052%

    No Known Activations