Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 84796
    Prev
    Next
    INDEX
    Explanations

    to and punctuation

    np_max-act · gemini-2.0-flash

    mathematical formulations of optimization problems.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects LaTeX math‐environment markup—especially the “subject to” constraint lines and related commands used when writing optimization problems in LaTeX.

    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
    ıyor
    -0.07
    láš
    -0.06
    のは
    -0.06
     (\<
    -0.06
    oldur
    -0.06
    .linspace
    -0.06
     textSize
    -0.06
    GameOver
    -0.06
     gio
    -0.06
    ゲーム
    -0.06
    POSITIVE LOGITS
     USART
    0.08
     temporarily
    0.08
    minor
    0.07
     assure
    0.07
     reminds
    0.07
     Prospect
    0.07
     AG
    0.07
    nginx
    0.06
     remind
    0.06
    .slice
    0.06
    Activations Density 0.006%

    No Known Activations