Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84530
    Prev
    Next
    INDEX
    Explanations

    olog

    np_max-act · gemini-2.0-flash

    This neuron detects the term “heterologous” (as used to describe genes, proteins, or expression systems).

    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
     Economics
    -0.06
    ,application
    -0.06
     towers
    -0.06
     tower
    -0.06
    (entities
    -0.06
     Recall
    -0.06
    .real
    -0.06
     requester
    -0.06
     Worcester
    -0.06
     Proposal
    -0.06
    POSITIVE LOGITS
    .unlink
    0.07
    เพ
    0.07
    밀
    0.06
     ↵  ↵
    0.06
     吉
    0.06
    qp
    0.06
     şeyler
    0.06
    [G
    0.06
    (getClass
    0.06
    .tcp
    0.06
    Activations Density 0.001%

    No Known Activations