© 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. 7276
    Prev
    Next
    INDEX
    Explanations

    help and advice

    np_max-act · gemini-2.0-flash

    instances of errors or inconsistencies in the conversation.

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

    This neuron is activated by phrases requesting or offering evidence or support for a claim.

    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
    振り
    -0.07
    Boxes
    -0.07
    bek
    -0.06
    じゃ
    -0.06
    ぐ
    -0.06
     confront
    -0.06
     RA
    -0.06
    EMA
    -0.06
    た
    -0.06
    shade
    -0.06
    POSITIVE LOGITS
     Đối
    0.07
    股
    0.07
    申博
    0.07
    _inode
    0.06
    _proxy
    0.06
     zarar
    0.06
    isser
    0.06
     impending
    0.06
     nied
    0.06
     zpráv
    0.06
    Activations Density 0.094%

    No Known Activations