© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 25351
    Prev
    Next
    INDEX
    Explanations

    code

    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
     butterfly
    -0.07
     immersion
    -0.07
    (material
    -0.07
     surf
    -0.07
     crawled
    -0.07
    .nome
    -0.07
     activation
    -0.07
    save
    -0.07
     september
    -0.06
     moments
    -0.06
    POSITIVE LOGITS
    pcb
    0.07
    _ES
    0.07
     Pros
    0.06
    个
    0.06
    τική
    0.06
     pcb
    0.06
    ideo
    0.06
    Formatting
    0.06
    arduino
    0.06
    packageName
    0.06
    Activations Density 0.000%

    No Known Activations