© 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
    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. 57836
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash

    descriptions of specific daily activities and events.

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

    The neuron flags negation and concessive cues—words like “not,” “weren’t,” and “either” that qualify or reverse statements.

    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
     music
    -0.06
    ContextMenu
    -0.06
    -west
    -0.06
    ("</
    -0.06
     </
    -0.06
    	expect
    -0.06
     assumed
    -0.06
    Monad
    -0.06
     lze
    -0.06
     مثال
    -0.06
    POSITIVE LOGITS
     approving
    0.07
     česk
    0.07
    .GroupLayout
    0.07
    快速
    0.07
     สพ
    0.07
     countertops
    0.06
    peria
    0.06
    .precision
    0.06
     Крас
    0.06
     cookbook
    0.06
    Activations Density 0.013%

    No Known Activations