© 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. 54149
    Prev
    Next
    INDEX
    Explanations

    bonus

    np_max-act · gemini-2.0-flash

    expressions and terms related to bonuses and incentives.

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

    This neuron detects occurrences of the word “bonus” (often in headings or labels).

    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
    vection
    -0.07
    	Color
    -0.07
     gravel
    -0.07
    _SL
    -0.07
     thick
    -0.07
    iteit
    -0.07
     PEOPLE
    -0.07
    Render
    -0.07
    DELETE
    -0.07
     React
    -0.07
    POSITIVE LOGITS
     Bonus
    0.14
     bonus
    0.13
    Bonus
    0.10
     Bon
    0.10
    bonus
    0.09
     bonuses
    0.09
    Bon
    0.08
     Bonnie
    0.08
    psz
    0.08
     bon
    0.07
    Activations Density 0.004%

    No Known Activations