© 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. 65190
    Prev
    Next
    INDEX
    Explanations

    eventually

    np_max-act · gemini-2.0-flash

    This neuron responds to narrative‐progression cues—especially adverbs like “suddenly,” temporal markers like “until,” and past‐tense/-ing verbs (e.g. “sitting”) that signal story action unfolding.

    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
    odate
    -0.07
    Band
    -0.07
     dõi
    -0.07
    isbn
    -0.06
     Nora
    -0.06
    lastName
    -0.06
    .telegram
    -0.06
    blue
    -0.06
    slug
    -0.06
    hum
    -0.06
    POSITIVE LOGITS
     результате
    0.08
    �
    0.07
    ...,
    0.06
    ●●●●●●●●
    0.06
     portrays
    0.06
    ,,,,,,,,
    0.06
     近
    0.06
     bietet
    0.06
    slots
    0.06
    .parametrize
    0.06
    Activations Density 0.056%

    No Known Activations