© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44385
    Prev
    Next
    INDEX
    Explanations

    exam results

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of official exam-related releases—terms like “Result,” “Answer Key,” “Admit Card,” “released,” and exam‐date tokens.

    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
    Physics
    -0.08
     proximity
    -0.07
    เศรษฐ
    -0.06
     reconnect
    -0.06
    plers
    -0.06
    ictions
    -0.06
    aad
    -0.06
     بالرياض
    -0.06
     claws
    -0.06
    (surface
    -0.06
    POSITIVE LOGITS
     Те
    0.07
    _ROOM
    0.07
    ше
    0.06
    ColumnName
    0.06
    (on
    0.06
     Sh
    0.06
    	B
    0.06
    #",
    0.06
     '=',
    0.06
     '''
    0.06
    Activations Density 0.007%

    No Known Activations