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. 123427
    Prev
    Next
    INDEX
    Explanations

    similar

    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
     vari
    -0.07
    @yahoo
    -0.06
    ;?>"
    -0.06
     Hermione
    -0.06
    ontent
    -0.06
     compatible
    -0.06
     마
    -0.06
    }'↵
    -0.06
    Connector
    -0.06
    ?>">
    ↵
    -0.06
    POSITIVE LOGITS
    839
    0.07
     trochu
    0.07
    ativ
    0.06
     rom
    0.06
    149
    0.06
     przy
    0.06
    597
    0.06
    717
    0.06
    吸
    0.06
    ۱۹۶
    0.06
    Activations Density 0.000%

    No Known Activations