© 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 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. 38782
    Prev
    Next
    INDEX
    Explanations

    plural

    np_max-act · gemini-2.0-flash

    This neuron detects the special markup tokens (e.g. the various <|start_header_id|>, <|end_header_id|>, etc.) used to delineate headers and segment boundaries in the 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
     nhờ
    -0.07
    West
    -0.07
    umont
    -0.06
    abh
    -0.06
    _sphere
    -0.06
    July
    -0.06
    Joy
    -0.06
     deny
    -0.06
     stages
    -0.06
    进一步
    -0.06
    POSITIVE LOGITS
     plural
    0.07
     massac
    0.07
    _quant
    0.06
    _SOC
    0.06
     кал
    0.06
     Torrent
    0.06
     دول
    0.06
     singular
    0.06
    _URI
    0.06
    iw
    0.06
    Activations Density 0.003%

    No Known Activations