© 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
    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. 5964
    Prev
    Next
    INDEX
    Explanations

    group

    np_max-act · gemini-2.0-flash

    the main thing this neuron does is detect mentions of chemical “groups,” i.e. references to functional groups like nitrile group, nitro group, electrophilic group, etc.

    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
     cca
    -0.07
    YYY
    -0.06
    Resp
    -0.06
     مما
    -0.06
     bitch
    -0.06
     curs
    -0.06
    eway
    -0.06
     المم
    -0.06
     missiles
    -0.06
    êm
    -0.06
    POSITIVE LOGITS
     благодаря
    0.07
    	sound
    0.07
    	map
    0.07
    .setPreferredSize
    0.06
     strtotime
    0.06
    strtotime
    0.06
     Graham
    0.06
    firstname
    0.06
    п
    0.06
     %%↵
    0.06
    Activations Density 0.007%

    No Known Activations