© 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. 90649
    Prev
    Next
    INDEX
    Explanations

    code, configurations

    np_max-act · gemini-2.0-flash

    The neuron fires on identifiers used as parameters or arguments in function/method definitions and calls.

    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
     inhib
    -0.07
    uve
    -0.07
    brakk
    -0.07
    atively
    -0.07
     {{$
    -0.07
    �
    -0.06
    _like
    -0.06
    HAV
    -0.06
     VIA
    -0.06
    _zeros
    -0.06
    POSITIVE LOGITS
    )};↵
    0.07
     anybody
    0.06
    _signature
    0.06
     Fishing
    0.06
     anyone
    0.06
     addicts
    0.06
     venta
    0.06
    ableViewController
    0.05
     reloadData
    0.05
    (random
    0.05
    Activations Density 0.013%

    No Known Activations