© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128570
    Prev
    Next
    INDEX
    Explanations

    judgement, determination

    np_max-act · gemini-2.0-flash

    The neuron activates on words referring to making judgments or decisions (e.g. “determination,” “decision,” “determine,” “judgment,” “verification”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    legal terminology and references to legal processes.

    oai_token-act-pair · gpt-4o-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
    _filtered
    -0.07
    рут
    -0.06
    _repr
    -0.06
    .getInput
    -0.06
     bổ
    -0.06
     най
    -0.06
     feel
    -0.06
    (scan
    -0.06
     meslek
    -0.06
     powder
    -0.06
    POSITIVE LOGITS
    анием
    0.07
     -*-
    ↵
    0.07
    460
    0.07
    ##↵↵
    0.07
     جغراف
    0.07
     gauche
    0.06
     nouvelle
    0.06
    ılığ
    0.06
     Border
    0.06
    /her
    0.06
    Activations Density 0.042%

    No Known Activations