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. 80672
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    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
     releg
    -0.07
    	mv
    -0.07
     Renders
    -0.06
     reinforced
    -0.06
    Mixed
    -0.06
     nosso
    -0.06
     الرو
    -0.06
    Studio
    -0.06
    ceries
    -0.06
     SYNC
    -0.06
    POSITIVE LOGITS
    .Bit
    0.06
     rites
    0.06
     проект
    0.06
    VK
    0.06
     intoler
    0.06
    _Utils
    0.06
    逸
    0.06
    がい
    0.06
     cit
    0.06
    /native
    0.06
    Activations Density 0.002%

    No Known Activations