© 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. 58817
    Prev
    Next
    INDEX
    Explanations

    emphasis

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “emphasis” (and its immediate context, e.g. “emphasis on”).

    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
    [maxn
    -0.07
     nhật
    -0.07
     viable
    -0.07
    (ro
    -0.06
    (q
    -0.06
    (j
    -0.06
    _create
    -0.06
    _flutter
    -0.06
    روب
    -0.06
    科
    -0.06
    POSITIVE LOGITS
     emphasis
    0.11
     emphas
    0.11
     emphasize
    0.11
     emphasized
    0.10
     emphasizing
    0.09
     emphasizes
    0.09
     emph
    0.08
    eman
    0.08
    emphasis
    0.07
    ampus
    0.07
    Activations Density 0.009%

    No Known Activations