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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58081
    Prev
    Next
    INDEX
    Explanations

    remarks comments

    np_max-act · gemini-2.0-flash

    references to political remarks or controversies surrounding influential figures.

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

    The neuron detects words that signal reported speech or commentary—terms like “remarks,” “comments,” “said,” and related markers of someone’s utterance.

    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
     recommend
    -0.07
    scan
    -0.07
    费用
    -0.07
    检测
    -0.06
    	object
    -0.06
     technology
    -0.06
    Fin
    -0.06
     розвиток
    -0.06
     индивиду
    -0.06
    	param
    -0.06
    POSITIVE LOGITS
    Remarks
    0.07
     remarks
    0.07
     remark
    0.07
     leo
    0.07
    ρίς
    0.06
    {_
    0.06
     somew
    0.06
     rowNum
    0.06
    _lua
    0.06
    /helpers
    0.06
    Activations Density 0.026%

    No Known Activations