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. 84482
    Prev
    Next
    INDEX
    Explanations

    book reviews

    np_max-act · gemini-2.0-flash

    literary elements and themes related to female empowerment and self-discovery within historical contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is pick out book‐review synopsis language—especially references to titles/authors and narrative summary cues (time spans, plot arcs, themes).

    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
     bugs
    -0.07
    Products
    -0.07
    .LogError
    -0.07
    CEF
    -0.06
    ("
    -0.06
    upd
    -0.06
    Stars
    -0.06
    .des
    -0.06
     CreateMap
    -0.06
    wrapped
    -0.06
    POSITIVE LOGITS
     кар
    0.07
    (JNIEnv
    0.06
    xec
    0.06
     Batch
    0.06
     rozh
    0.06
     ASCII
    0.06
     Gus
    0.06
    .getFullYear
    0.06
    ิมพ
    0.06
     Erik
    0.06
    Activations Density 0.027%

    No Known Activations