© 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. 91514
    Prev
    Next
    INDEX
    Explanations

    Opening brackets

    np_max-act · gemini-2.0-flash

    This neuron detects LaTeX‐style mathematical expressions, especially tokens inside math formulas (e.g. backslash commands, braces, and symbol sequences).

    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
     papers
    -0.06
     bile
    -0.06
     Lovely
    -0.06
    Ocean
    -0.06
     intens
    -0.06
    ậu
    -0.06
    Mind
    -0.06
     sahip
    -0.06
     independent
    -0.05
    黎
    -0.05
    POSITIVE LOGITS
    ？”
    0.07
    _fecha
    0.07
    ？」
    0.07
    addGroup
    0.07
    Ubuntu
    0.07
    _Panel
    0.07
    för
    0.06
    (--
    0.06
    BackColor
    0.06
     gezocht
    0.06
    Activations Density 0.007%

    No Known Activations