© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109800
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    This neuron identifies numeric data—especially survey statistics and percentages.

    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
    ETY
    -0.07
    Unsupported
    -0.07
    /payment
    -0.07
    ucene
    -0.06
    .App
    -0.06
    difficulty
    -0.06
    icamente
    -0.06
    　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　　
    -0.06
    persona
    -0.06
     düzen
    -0.06
    POSITIVE LOGITS
     europé
    0.07
     features
    0.06
    Feat
    0.06
     sebep
    0.06
     geography
    0.06
    行動
    0.06
     benefiting
    0.06
     $('.
    0.06
    _ib
    0.06
    $('.
    0.06
    Activations Density 0.016%

    No Known Activations