Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13287
    Prev
    Next
    INDEX
    Explanations

    forward slash

    np_max-act · gemini-2.0-flash

    The neuron fires on the slash (“/”) tokens that serve as directory separators in filesystem paths.

    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
    rezent
    -0.08
    <form
    -0.07
     vyk
    -0.06
     prosecutors
    -0.06
    ial
    -0.06
     tekn
    -0.06
     psik
    -0.06
    cob
    -0.06
    licos
    -0.06
     judged
    -0.06
    POSITIVE LOGITS
    )^
    0.07
    にか
    0.06
    fiction
    0.06
     warp
    0.06
    .drawString
    0.06
    /"
    0.06
    -motion
    0.06
     assumption
    0.06
    ertility
    0.06
    _SUFFIX
    0.06
    Activations Density 0.001%

    No Known Activations