© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12724
    Prev
    Next
    INDEX
    Explanations

    approved

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of formal study approval (e.g., ethics or institutional review board approval statements).

    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
     maduras
    -0.07
    ,char
    -0.07
    Criterion
    -0.06
    .*)
    -0.06
     EITHER
    -0.06
    etection
    -0.06
     krev
    -0.06
    ENE
    -0.06
    _rp
    -0.06
     Cy
    -0.06
    POSITIVE LOGITS
     hath
    0.06
     Neh
    0.06
     colabor
    0.06
     access
    0.06
     approved
    0.06
     récup
    0.06
     needed
    0.06
     AFF
    0.06
    TAG
    0.06
     Ya
    0.06
    Activations Density 0.001%

    No Known Activations