© 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. 42766
    Prev
    Next
    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash

    This neuron detects regex character‐class tokens and related metacharacters (e.g. “[”, “]”, “[:”, “:]”, “^” inside classes, backslash escapes, and the dot) used to define or invert character classes.

    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
     dropout
    -0.07
    ляем
    -0.07
    _dest
    -0.06
    _THREAD
    -0.06
    Lic
    -0.06
    ‚ط
    -0.06
     rings
    -0.06
    tokenId
    -0.06
    άλ
    -0.06
     flushing
    -0.06
    POSITIVE LOGITS
     ConfigureServices
    0.08
    sciously
    0.07
     Scouts
    0.07
     elek
    0.07
    》
    0.06
     SETTINGS
    0.06
     deceased
    0.06
     Tarif
    0.06
     JQuery
    0.06
     Latest
    0.06
    Activations Density 0.007%

    No Known Activations