© 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. 6508
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash

    This neuron highlights the key content words—chiefly nouns, verbs, and adjectives—that carry the main points or “gist” of the speaker’s explanation.

    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
     Table
    -0.07
    ivol
    -0.06
     Won
    -0.06
    �
    -0.06
    397
    -0.06
     infra
    -0.06
     Dw
    -0.06
    Asc
    -0.06
    ADV
    -0.06
     Bah
    -0.06
    POSITIVE LOGITS
     GLenum
    0.06
    真的
    0.06
     mann
    0.06
     ноя
    0.06
    ุทธ
    0.06
    باز
    0.06
    (Common
    0.06
     regret
    0.06
    <Integer
    0.06
     crude
    0.06
    Activations Density 0.012%

    No Known Activations