© 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. 92317
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash

    The neuron fires on short, general-purpose discourse cues—single words like “it,” “does,” “well,” “that,” or “because” used to start or link clauses.

    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
    logradouro
    -0.07
    _added
    -0.07
    Frozen
    -0.07
     Heroes
    -0.07
    ->___
    -0.07
    [][
    -0.06
     resurgence
    -0.06
     lå
    -0.06
     MUSIC
    -0.06
     Collective
    -0.06
    POSITIVE LOGITS
    /apache
    0.07
     drive
    0.06
    ']},↵
    0.06
    Nie
    0.06
     isc
    0.06
     DVR
    0.06
    .alloc
    0.06
    imports
    0.06
     돌
    0.06
    >");↵↵
    0.06
    Activations Density 0.034%

    No Known Activations