© 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
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 127062
    Prev
    Next
    INDEX
    Explanations

    mathematical/scientific formulas, 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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mundane
    -0.07
    Deletes
    -0.06
    _tests
    -0.06
     transformative
    -0.06
     dots
    -0.06
    Dia
    -0.06
     jer
    -0.06
     Praha
    -0.06
     capsules
    -0.06
    	args
    -0.06
    POSITIVE LOGITS
     corres
    0.07
    ệ
    0.06
     Ly
    0.06
     ری
    0.06
     racer
    0.06
    SELL
    0.06
    Reporting
    0.06
     philanth
    0.06
     goalt
    0.06
     ‫
    0.06
    Activations Density 0.036%

    No Known Activations