© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 62049
    Prev
    Next
    INDEX
    Explanations

    usually

    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
    _plot
    -0.07
    	bs
    -0.07
    """↵↵↵
    -0.07
    _placement
    -0.06
    submitted
    -0.06
    -control
    -0.06
    cadena
    -0.06
    (""
    -0.06
    	main
    -0.06
    Difference
    -0.06
    POSITIVE LOGITS
     usually
    0.07
     Num
    0.07
    iability
    0.06
    .Mapper
    0.06
     proverb
    0.06
     terug
    0.06
     normally
    0.06
     numOf
    0.06
    .borrow
    0.06
     tây
    0.06
    Activations Density 0.088%

    No Known Activations