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. 30247
    Prev
    Next
    INDEX
    Explanations

    logic expressions

    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
    holds
    -0.07
     رفت
    -0.07
     zatímco
    -0.07
    ových
    -0.06
     DOMAIN
    -0.06
     hurried
    -0.06
    capt
    -0.06
     çevres
    -0.06
     dinh
    -0.06
    virtual
    -0.06
    POSITIVE LOGITS
    .blit
    0.07
    state
    0.06
    Criterion
    0.06
    .ep
    0.06
    くと
    0.06
     Preparation
    0.06
    	score
    0.06
    /python
    0.06
     ifdef
    0.06
    ErrorCode
    0.06
    Activations Density 0.013%

    No Known Activations