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. 86004
    Prev
    Next
    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash

    elements related to game modification and enhancements.

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

    The neuron fires on descriptive terms for adding or improving features—e.g. “change,” “new,” “improving,” “adding”—as found in mod/change‐log style text.

    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
     onAnimation
    -0.06
    Scripts
    -0.06
     İran
    -0.06
     themed
    -0.06
    álie
    -0.06
    UsageId
    -0.06
    vím
    -0.06
    _HandleTypeDef
    -0.06
    .enable
    -0.06
     AOL
    -0.06
    POSITIVE LOGITS
     closing
    0.08
     mehr
    0.08
     напря
    0.07
     anale
    0.07
    Uniform
    0.07
    十
    0.06
    minimal
    0.06
    usiness
    0.06
     mapped
    0.06
     opaque
    0.06
    Activations Density 0.013%

    No Known Activations