© 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. 109656
    Prev
    Next
    INDEX
    Explanations

    protect

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “protect” or “protection” (i.e. words conveying protection).

    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
     forms
    -0.07
     salads
    -0.06
     Comet
    -0.06
    $item
    -0.06
    /preferences
    -0.06
     dagen
    -0.06
    azer
    -0.06
     advice
    -0.06
    illustr
    -0.06
     leasing
    -0.06
    POSITIVE LOGITS
    ,/
    0.07
     grpc
    0.07
    315
    0.07
    ?”↵↵
    0.07
     Vince
    0.06
    (dispatch
    0.06
     Img
    0.06
    /sh
    0.06
    西
    0.06
     }
    0.06
    Activations Density 0.018%

    No Known Activations