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. 15-RESID-POST-AA
    6. 111081
    Prev
    Next
    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash

    negation words or discussions of negative aspects, absences, and missing information.

    oai_token-act-pair · claude-4-5-haikuTriggered by @bowenyi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     적용
    -0.06
    illator
    -0.06
     analytical
    -0.06
    اطعة
    -0.06
    章
    -0.06
     seriously
    -0.06
    Orange
    -0.06
     нег
    -0.06
    odial
    -0.06
    クラ
    -0.06
    POSITIVE LOGITS
    (src
    0.06
    )%
    0.06
     Forced
    0.06
    _plural
    0.06
    ımıza
    0.06
    ITA
    0.06
     jar
    0.06
     synerg
    0.06
    -san
    0.06
    .UserInfo
    0.06
    Activations Density 0.585%

    No Known Activations