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. 54235
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    aneous
    -0.06
    회
    -0.06
     Appe
    -0.06
    	mutex
    -0.06
    baz
    -0.06
    BadRequest
    -0.06
    غط
    -0.06
     serotonin
    -0.06
    CUS
    -0.06
    utsche
    -0.06
    POSITIVE LOGITS
    discover
    0.07
    サイズ
    0.07
    (itemId
    0.07
    filt
    0.07
     blowing
    0.07
     communications
    0.07
     लग
    0.06
    گان
    0.06
     �
    0.06
    education
    0.06
    Activations Density 0.015%

    No Known Activations