© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42539
    Prev
    Next
    INDEX
    Explanations

    Knowledge/awareness

    np_max-act · gemini-2.0-flash

    The neuron fires on words and small phrases that signal novelty or speculative suggestion (e.g. “innovative,” “not yet thought about,” “about”).

    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
     �
    -0.07
     Fired
    -0.06
     své
    -0.06
    ’de
    -0.06
     Bennett
    -0.06
    (feed
    -0.06
    .toJson
    -0.06
    \Tests
    -0.06
     assertEquals
    -0.06
    _kses
    -0.06
    POSITIVE LOGITS
     Minist
    0.06
    indsay
    0.06
     guests
    0.06
    fans
    0.06
     heats
    0.06
    (a
    0.06
    inar
    0.06
     metaphor
    0.06
     ministries
    0.06
     Населення
    0.06
    Activations Density 0.028%

    No Known Activations