© 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. 126251
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to biochemical enzyme names, specifically tokens ending in the “-ase” suffix.

    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
    Warm
    -0.06
    ${
    -0.06
     gust
    -0.06
    Effects
    -0.06
    Bound
    -0.06
    Pale
    -0.06
    successfully
    -0.06
     pier
    -0.06
    _dx
    -0.06
    amics
    -0.06
    POSITIVE LOGITS
    (Max
    0.07
     запас
    0.06
    GRAM
    0.06
    .extent
    0.06
     fotoğraf
    0.06
    .Headers
    0.06
    .getChildAt
    0.06
    phase
    0.06
    addin
    0.06
    existence
    0.06
    Activations Density 0.059%

    No Known Activations