© 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. 38526
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron fires on words and short phrases that introduce a proposed action or solution (e.g. “To address this,” “we propose,” “In response to this”).

    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
    IZATION
    -0.06
    Christian
    -0.06
     LIKE
    -0.06
    RON
    -0.06
     Stand
    -0.06
     heaven
    -0.06
     Graf
    -0.06
     Sisters
    -0.05
     basics
    -0.05
     runaway
    -0.05
    POSITIVE LOGITS
    ład
    0.07
     persone
    0.07
    ég
    0.07
    olumes
    0.07
     зокрема
    0.06
    _tag
    0.06
    &t
    0.06
     Cells
    0.06
    ата
    0.06
    (resolve
    0.06
    Activations Density 0.065%

    No Known Activations