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. 15-RESID-POST-AA
    6. 110327
    Prev
    Next
    INDEX
    Explanations

    Conversational/Q&A context

    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
    Annotations
    -0.07
     центр
    -0.06
    (geometry
    -0.06
     чоловік
    -0.06
     enhancements
    -0.06
     progress
    -0.06
     callee
    -0.06
     işe
    -0.06
    ital
    -0.06
    entieth
    -0.06
    POSITIVE LOGITS
    ujet
    0.06
     महत
    0.06
     [-
    0.06
     drip
    0.06
    );}↵↵
    0.06
    Ended
    0.06
    :bg
    0.06
    alin
    0.06
    =&
    0.06
     case
    0.06
    Activations Density 0.071%

    No Known Activations