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. 54354
    Prev
    Next
    INDEX
    Explanations

    claim

    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
    Kn
    -0.07
     gerade
    -0.07
    �
    -0.06
     Opp
    -0.06
    赵
    -0.06
     tote
    -0.06
     Diana
    -0.06
     explain
    -0.06
     hometown
    -0.06
    .ast
    -0.06
    POSITIVE LOGITS
     claim
    0.07
     saying
    0.06
     请求
    0.06
    count
    0.06
     claiming
    0.06
     '+'
    0.06
     Indi
    0.06
    (formatter
    0.06
    .once
    0.06
    _based
    0.06
    Activations Density 0.008%

    No Known Activations