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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127033
    Prev
    Next
    INDEX
    Explanations

    "cozy" and "snuggling"

    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
     Benef
    -0.07
     slik
    -0.07
     Skip
    -0.06
    _out
    -0.06
    -rating
    -0.06
    *)
    -0.06
     ignited
    -0.06
     forgot
    -0.06
     \$
    -0.06
     FLASH
    -0.06
    POSITIVE LOGITS
     cozy
    0.08
    _original
    0.07
     StatusBar
    0.07
    gil
    0.07
    EditMode
    0.07
    &m
    0.07
    spd
    0.07
    Strategy
    0.06
     lockdown
    0.06
     AJ
    0.06
    Activations Density 0.006%

    No Known Activations