© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58640
    Prev
    Next
    INDEX
    Explanations

    Data analysis/reporting

    np_max-act · gemini-2.0-flash

    This neuron activates on the special “<|start_header_id|>” token that marks the start of a header ID, i.e. it detects the internal header‐ID marker.

    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
     StringBuffer
    -0.07
    .Visual
    -0.06
     glitch
    -0.06
     NAN
    -0.06
     laz
    -0.06
     clo
    -0.06
    _ts
    -0.06
    ább
    -0.06
    urses
    -0.06
     температура
    -0.06
    POSITIVE LOGITS
    jejer
    0.07
     flatten
    0.07
    문제
    0.06
    -posts
    0.06
     Seks
    0.06
     diamond
    0.06
    queries
    0.06
     трансп
    0.06
    -с
    0.06
     Ellie
    0.06
    Activations Density 0.033%

    No Known Activations