© 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
    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. 42738
    Prev
    Next
    INDEX
    Explanations

    enumerated lists

    np_max-act · gemini-2.0-flash

    This neuron detects parenthesized enumeration markers (e.g., numbered or roman‐numeral list indices like “(ii)”, “(3)”, etc.).

    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
    bp
    -0.07
     conoc
    -0.07
    please
    -0.06
    lower
    -0.06
    Return
    -0.06
     pound
    -0.06
     alarming
    -0.06
    (the
    -0.06
    geç
    -0.06
    jpeg
    -0.06
    POSITIVE LOGITS
     永
    0.07
    _bug
    0.07
    UCKET
    0.07
    spath
    0.06
     广
    0.06
     altru
    0.06
    ):?>↵
    0.06
     머
    0.06
    <ArrayList
    0.06
     story
    0.06
    Activations Density 0.016%

    No Known Activations