© 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. 108782
    Prev
    Next
    INDEX
    Explanations

    making changes

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on tokens in cautionary or side‐note–style instruction passages (e.g. after “Note:,” in advisory explanations or warnings).

    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
    ्ज
    -0.07
    Cas
    -0.07
    ertoire
    -0.06
    Bid
    -0.06
    ologue
    -0.06
    μφ
    -0.06
    onic
    -0.06
    ึง
    -0.06
     έν
    -0.06
     기억
    -0.06
    POSITIVE LOGITS
     currentNode
    0.09
    =url
    0.07
    -----------
↵
    0.07
     restrict
    0.06
    (dec
    0.06
     lỗi
    0.06
     dlou
    0.06
     yıldır
    0.06
    pering
    0.06
    /mp
    0.06
    Activations Density 0.042%

    No Known Activations