© 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. 57828
    Prev
    Next
    INDEX
    Explanations

    Story excerpts

    np_max-act · gemini-2.0-flash

    expressions of gratitude and support in interactions.

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

    This neuron responds to punctuation marks—especially end-of-sentence periods—marking sentence boundaries.

    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
     Houses
    -0.08
     Flames
    -0.07
    ";↵↵↵
    -0.07
    Lookup
    -0.07
    aturdays
    -0.07
    fst
    -0.07
    ुभ
    -0.06
     Ryder
    -0.06
    ую
    -0.06
    ΑΙ
    -0.06
    POSITIVE LOGITS
     Json
    0.06
    ',{'
    0.06
     architekt
    0.06
    quite
    0.06
    llib
    0.06
     点
    0.06
     resultat
    0.06
    .Redirect
    0.05
     adam
    0.05
    .pages
    0.05
    Activations Density 0.081%

    No Known Activations