© 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. 42764
    Prev
    Next
    INDEX
    Explanations

    contacting/submitting

    np_max-act · gemini-2.0-flash

    The neuron fires on call-to-action verbs in instructions—words like “contact,” “submit,” “request,” or “discuss” that prompt the reader to take action.

    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
    keypress
    -0.07
    arsity
    -0.06
    」的
    -0.06
    .shopping
    -0.06
    ürger
    -0.06
    .Rows
    -0.06
    irus
    -0.06
    anut
    -0.06
    UserId
    -0.06
    895
    -0.06
    POSITIVE LOGITS
     म
    0.06
     jal
    0.06
    ,,,,
    0.06
    mr
    0.06
    บาล
    0.06
    Switch
    0.06
    autoreleasepool
    0.06
    _criteria
    0.06
    _EOL
    0.06
    O
    0.06
    Activations Density 0.025%

    No Known Activations