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. 54429
    Prev
    Next
    INDEX
    Explanations

    withholding

    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
    离开
    -0.07
     разви
    -0.07
     gpointer
    -0.07
    ังกล
    -0.06
     peque
    -0.06
    ไฟล
    -0.06
     eder
    -0.06
    StateMachine
    -0.06
     succès
    -0.06
    目录
    -0.06
    POSITIVE LOGITS
     withholding
    0.10
     withhold
    0.09
     withheld
    0.09
     onset
    0.07
    _fn
    0.07
    tok
    0.07
    .bits
    0.07
     ^=
    0.07
    /command
    0.07
    .on
    0.06
    Activations Density 0.002%

    No Known Activations