© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110562
    Prev
    Next
    INDEX
    Explanations

    math formulas

    np_max-act · gemini-2.0-flash

    This neuron detects the presence of numerical expressions—like equation references, parameter names, and numeric values—in the text.

    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
    ARING
    -0.07
    _cmp
    -0.07
    /Set
    -0.06
    .Stream
    -0.06
    期待
    -0.06
     pien
    -0.06
    Textarea
    -0.06
    .transactions
    -0.06
    -middle
    -0.06
    Ohio
    -0.06
    POSITIVE LOGITS
     pard
    0.07
     styling
    0.07
     efficiency
    0.06
     Protocol
    0.06
    $pdf
    0.06
    �单
    0.06
    "]);↵
    0.06
    pción
    0.06
    }/>↵
    0.06
    -org
    0.06
    Activations Density 0.015%

    No Known Activations