© 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. 110141
    Prev
    Next
    INDEX
    Explanations

    illnesses

    np_max-act · gemini-2.0-flash

    The neuron activates on terms naming illnesses, symptoms, and medicinal uses—that is, words in contexts describing medical conditions or remedies.

    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
    いる
    -0.07
    affected
    -0.07
    価
    -0.06
    erson
    -0.06
    兹
    -0.06
    яти
    -0.06
    人
    -0.06
    翼
    -0.06
    postal
    -0.06
    sets
    -0.06
    POSITIVE LOGITS
    RunWith
    0.07
     UIB
    0.06
    (sb
    0.06
    Additional
    0.06
    itted
    0.06
    <dyn
    0.06
    -public
    0.06
    _empresa
    0.06
     Follow
    0.06
    stile
    0.06
    Activations Density 0.021%

    No Known Activations