© 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. 11-RESID-POST-AA
    11. 126927
    Prev
    Next
    INDEX
    Explanations

    erroneous

    np_max-act · gemini-2.0-flash

    The neuron responds to technical safety‐and‐risk terms—particularly mentions of “erroneous puncture” and related indwelling needle safety language.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     booty
    -0.06
    taking
    -0.06
    atitis
    -0.05
     pus
    -0.05
    ppelin
    -0.05
    texture
    -0.05
     Tây
    -0.05
     gp
    -0.05
     fclose
    -0.05
    小说
    -0.05
    POSITIVE LOGITS
     самостоятель
    0.07
     Savaşı
    0.07
    HTTP
    0.07
     feu
    0.07
    necessary
    0.07
     때
    0.07
     interes
    0.07
    adjust
    0.06
     Belle
    0.06
    ный
    0.06
    Activations Density 0.174%

    No Known Activations