© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73551
    Prev
    Next
    INDEX
    Explanations

    theory/analysis

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of theoretical analysis or formal evaluation, highlighting discussion of proofs, bounds, or analytical insights.

    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
     DRIVER
    -0.06
     personally
    -0.06
     dynamically
    -0.06
    freeze
    -0.06
     ButterKnife
    -0.06
     Dylan
    -0.06
     disappe
    -0.06
     NOTE
    -0.06
    .Registry
    -0.06
    -bind
    -0.05
    POSITIVE LOGITS
    .cli
    0.07
    民
    0.07
    短
    0.07
     récup
    0.07
    -auto
    0.07
    _seg
    0.07
    城
    0.07
     alanı
    0.07
    极
    0.06
    (Sender
    0.06
    Activations Density 0.060%

    No Known Activations