© 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. 125139
    Prev
    Next
    INDEX
    Explanations

    label

    np_max-act · gemini-2.0-flash

    The neuron identifies mentions of labeling or tagging (e.g. “label,” “labels,” “label-free,” “tagging”) in the context of detection methods.

    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
     depends
    -0.07
     melting
    -0.07
     Ult
    -0.07
     tamam
    -0.06
     shadow
    -0.06
    意见
    -0.06
     thrust
    -0.06
    vět
    -0.06
     bc
    -0.06
    butt
    -0.06
    POSITIVE LOGITS
    相關
    0.07
    ิตย
    0.07
    ayız
    0.07
     계약
    0.06
    _ACTIVITY
    0.06
    telefone
    0.06
    АР
    0.06
    @implementation
    0.06
    .ul
    0.06
    currentTime
    0.06
    Activations Density 0.006%

    No Known Activations