© 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. 73892
    Prev
    Next
    INDEX
    Explanations

    assumptions

    np_max-act · gemini-2.0-flash

    The neuron detects conditional or hypothetical framing words (like “if,” “assuming,” etc.) that introduce assumptions.

    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
     soukrom
    -0.07
     statusBar
    -0.07
    wild
    -0.07
     bourbon
    -0.06
     причин
    -0.06
     itemView
    -0.06
    -public
    -0.06
     grat
    -0.06
     cubic
    -0.06
     yatır
    -0.06
    POSITIVE LOGITS
    (:,:,
    0.07
    _instruction
    0.07
    .star
    0.07
     var
    0.07
    *R
    0.06
     copied
    0.06
    _counts
    0.06
    _SELECTED
    0.06
    .nick
    0.06
     lại
    0.06
    Activations Density 0.131%

    No Known Activations