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. 53767
    Prev
    Next
    INDEX
    Explanations

    national

    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
    585
    -0.08
     towers
    -0.07
     fold
    -0.06
    563
    -0.06
     crochet
    -0.06
     Opp
    -0.06
    323
    -0.06
    985
    -0.06
     kdo
    -0.06
     عن
    -0.06
    POSITIVE LOGITS
     �
    0.07
    !↵↵↵
    0.07
     ragaz
    0.07
    ");}↵
    0.06
    _production
    0.06
    ・━・━・━・━
    0.06
    EntityType
    0.06
    .bucket
    0.06
     světa
    0.06
    .toDouble
    0.06
    Activations Density 0.109%

    No Known Activations