© 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. 15-RESID-POST-AA
    11. 34106
    Prev
    Next
    INDEX
    Explanations

    preservative

    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
     MF
    -0.06
     Increasing
    -0.06
    нд
    -0.06
    renched
    -0.06
    ็อก
    -0.06
     Feedback
    -0.06
    jets
    -0.06
    aud
    -0.06
     wollen
    -0.06
     journals
    -0.06
    POSITIVE LOGITS
    	res
    0.08
    เหล
    0.07
     世
    0.07
     ".$_
    0.06
    lerce
    0.06
     свер
    0.06
     serializer
    0.06
     خارجية
    0.06
    —"
    0.06
    /arm
    0.06
    Activations Density 0.007%

    No Known Activations