© 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. 876
    Prev
    Next
    INDEX
    Explanations

    medical symptoms

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of adverse health symptoms (e.g., coughing, redness, itching) in the text.

    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
     GIVEN
    -0.07
     Vog
    -0.07
    :selected
    -0.07
     IsValid
    -0.07
     cautioned
    -0.06
    uglify
    -0.06
     Darling
    -0.06
     sisters
    -0.06
    .setName
    -0.06
     convicted
    -0.06
    POSITIVE LOGITS
    .Window
    0.07
     είχε
    0.06
    (confirm
    0.06
    ハ
    0.06
    .xlabel
    0.06
     orig
    0.06
     gle
    0.06
    DbContext
    0.06
    .setError
    0.06
     aria
    0.05
    Activations Density 0.007%

    No Known Activations