© 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. 30738
    Prev
    Next
    INDEX
    Explanations

    computer code and instructions

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on document-structure markers—especially header labels like “Context:” and similar metadata tokens—identifying section‐header or formatting markers rather than the main 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
    .audio
    -0.09
    라인
    -0.07
    られ
    -0.07
    ственных
    -0.07
    ственные
    -0.06
    .circular
    -0.06
    ý
    -0.06
    ystems
    -0.06
    983
    -0.06
     agon
    -0.06
    POSITIVE LOGITS
    .Constant
    0.07
    !!↵↵
    0.07
     translateY
    0.07
    $res
    0.07
     підготов
    0.06
     член
    0.06
     vene
    0.06
    <Scalars
    0.06
     fallout
    0.06
     DIRECTORY
    0.06
    Activations Density 0.045%

    No Known Activations