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. 84534
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on long, domain-specific technical terms (scientific jargon).

    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
    ott
    -0.07
     sleeve
    -0.07
    ega
    -0.06
    Sorting
    -0.06
    CTR
    -0.06
    CT
    -0.06
    DIC
    -0.06
    ”.↵
    -0.06
     Cait
    -0.06
    interfaces
    -0.06
    POSITIVE LOGITS
    (web
    0.06
     місці
    0.06
     şu
    0.06
     Julio
    0.06
    ุญาต
    0.06
     その他
    0.06
    国際
    0.06
     знову
    0.06
     readiness
    0.06
     carta
    0.06
    Activations Density 0.114%

    No Known Activations