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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 123124
    Prev
    Next
    INDEX
    Explanations

    tasting drinks

    np_max-act · gemini-2.0-flash
    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
    افة
    -0.06
    igest
    -0.06
    odule
    -0.06
    егра
    -0.06
    aciones
    -0.06
    ils
    -0.06
     liền
    -0.06
    _quest
    -0.06
     ост
    -0.06
    ,text
    -0.06
    POSITIVE LOGITS
     presented
    0.07
     inexperienced
    0.07
     independents
    0.07
    меш
    0.07
     devel
    0.07
    (wp
    0.07
     Define
    0.07
     SNP
    0.07
     رفع
    0.06
    不是
    0.06
    Activations Density 0.083%

    No Known Activations