© 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. 55940
    Prev
    Next
    INDEX
    Explanations

    Question and answer snippets

    np_max-act · gemini-2.0-flash

    This neuron detects error or exception message tokens (e.g. names, colons, and class‐style separators commonly found in log or stack trace headers).

    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
    cookie
    -0.06
     piece
    -0.06
     Control
    -0.06
     residuals
    -0.06
     Morton
    -0.06
    __$
    -0.06
     Flight
    -0.06
    -grid
    -0.06
     control
    -0.06
     Spawn
    -0.06
    POSITIVE LOGITS
    .wik
    0.07
     '');
    0.07
     Horror
    0.06
    ЛА
    0.06
    ニﾆ
    0.06
    izm
    0.06
     GUIDATA
    0.06
     Infragistics
    0.06
     Québec
    0.06
    ลด
    0.06
    Activations Density 0.037%

    No Known Activations