© 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. 129808
    Prev
    Next
    INDEX
    Explanations

    biological classifications

    np_max-act · gemini-2.0-flash

    This neuron detects taxonomic family or subfamily names (e.g., those ending in “idae” or “inae”).

    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
    orizontal
    -0.07
    utivo
    -0.07
     pastoral
    -0.06
    :self
    -0.06
    >Title
    -0.06
    angelog
    -0.06
    umidity
    -0.06
    assy
    -0.06
     कहन
    -0.06
     newspapers
    -0.06
    POSITIVE LOGITS
     defense
    0.07
    usually
    0.07
     sou
    0.06
    PBS
    0.06
    defense
    0.06
     час
    0.06
     бел
    0.06
     önceki
    0.06
     concaten
    0.06
    ırken
    0.06
    Activations Density 0.006%

    No Known Activations