© 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. 23064
    Prev
    Next
    INDEX
    Explanations

    search queries

    np_max-act · gemini-2.0-flash

    indications of software or programming-related topics.

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

    The neuron flags instructions to look something up—tokens like “search,” “searching,” “find,” “for,” or related query suggestions guiding the user to search online.

    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
    perial
    -0.07
    SCRIPTION
    -0.07
    	mc
    -0.07
     Ches
    -0.07
    .back
    -0.07
     rat
    -0.07
     Assuming
    -0.06
    "].(
    -0.06
    cur
    -0.06
     Imperial
    -0.06
    POSITIVE LOGITS
    150
    0.06
    LIBINT
    0.06
     ENABLE
    0.06
    -navbar
    0.06
    镇
    0.06
    Glyph
    0.06
    같
    0.06
    Lint
    0.06
    TestMethod
    0.06
     ổn
    0.06
    Activations Density 0.012%

    No Known Activations