© 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. 44944
    Prev
    Next
    INDEX
    Explanations

    unit

    np_max-act · gemini-2.0-flash

    the neuron selectively detects mentions of molecular “subunit(s)” (especially receptor or ion‐channel subunits) in biomedical text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    content related to specific receptor subunits in the central nervous system and their implications in various physiological conditions.

    oai_token-act-pair · gpt-4o-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
    	afx
    -0.07
    ANY
    -0.07
    :",
    -0.06
    Knowledge
    -0.06
    G
    -0.06
    ATEG
    -0.06
     diseases
    -0.06
    古
    -0.06
    ::$
    -0.06
    꾸
    -0.06
    POSITIVE LOGITS
     Ủy
    0.07
     حف
    0.07
     Hunt
    0.07
    unit
    0.06
     unilateral
    0.06
     підт
    0.06
     teammate
    0.06
     Seahawks
    0.06
    abl
    0.06
     Üy
    0.06
    Activations Density 0.002%

    No Known Activations