© 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. 7-RESID-POST-AA
    11. 115745
    Prev
    Next
    INDEX
    Explanations

    submissive

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äh
    -0.06
    ่วน
    -0.06
     walnut
    -0.06
     ست
    -0.06
    .register
    -0.06
     gep
    -0.06
    ki
    -0.06
    _der
    -0.06
    331
    -0.06
    _'.$
    -0.06
    POSITIVE LOGITS
     submissive
    0.13
     лов
    0.07
    umble
    0.07
     Ninth
    0.06
    <|eot_id|>
    0.06
    >window
    0.06
     освещ
    0.06
     simmer
    0.06
     kc
    0.06
    	Transform
    0.06
    Activations Density 0.005%

    No Known Activations