© 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. 22893
    Prev
    Next
    INDEX
    Explanations

    light

    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
     Abbas
    -0.07
     Ranch
    -0.07
     Tennessee
    -0.07
     succeeding
    -0.06
    enario
    -0.06
     ankle
    -0.06
     Böylece
    -0.06
     Benn
    -0.06
     poo
    -0.06
     elem
    -0.06
    POSITIVE LOGITS
     light
    0.14
    Light
    0.13
     Light
    0.12
     LIGHT
    0.11
    -light
    0.10
    light
    0.10
    LIGHT
    0.09
     lights
    0.09
    (light
    0.08
    	light
    0.08
    Activations Density 0.046%

    No Known Activations