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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27-RESID-POST-AA
    11. 12900
    Prev
    Next
    INDEX
    Explanations

    gardens and parks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arcpy
    -0.07
    _COLUMNS
    -0.07
    /E
    -0.07
    _comment
    -0.07
    =output
    -0.06
    	angle
    -0.06
     Його
    -0.06
    	public
    -0.06
    (W
    -0.06
    roperties
    -0.06
    POSITIVE LOGITS
     чим
    0.06
     東京
    0.06
     snaps
    0.06
     NOR
    0.06
     τον
    0.06
     anymore
    0.06
     sơ
    0.06
     downgrade
    0.06
    nym
    0.06
     Describe
    0.06
    Activations Density 0.034%

    No Known Activations