Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RESID-POST-AA
    6. 100397
    Prev
    Next
    INDEX
    Explanations

    as

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enters
    -0.07
    ━━
    -0.06
     entering
    -0.06
     Surg
    -0.06
    .stop
    -0.06
     ا
    -0.06
     nowrap
    -0.06
    _PUS
    -0.06
    rica
    -0.06
     lept
    -0.06
    POSITIVE LOGITS
    valuator
    0.06
     Oakland
    0.06
    계
    0.06
     Might
    0.06
     heel
    0.06
     unrecognized
    0.06
     maduras
    0.06
     علمی
    0.06
     dre
    0.06
    対
    0.06
    Activations Density 0.011%

    No Known Activations