© 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 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. 38792
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the root “disestablish” (e.g. “disestablish,” “disestablished”) in category or category‐like lines.

    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
    <Point
    -0.07
     душ
    -0.06
     Necessary
    -0.06
     англ
    -0.06
     congressional
    -0.06
     cầu
    -0.06
     Halloween
    -0.06
     requirements
    -0.06
    bookmark
    -0.06
    .setRotation
    -0.06
    POSITIVE LOGITS
    ляет
    0.07
    
    0.06
     teil
    0.06
     instincts
    0.06
    erts
    0.06
     territorial
    0.06
    RIEND
    0.06
    ICTURE
    0.06
    ordum
    0.06
     clr
    0.06
    Activations Density 0.001%

    No Known Activations