© 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 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. 57098
    Prev
    Next
    INDEX
    Explanations

    od

    np_max-act · gemini-2.0-flash

    terms related to stem cell research and differentiation, specifically in the context of pancreatic and liver cells.

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

    This neuron detects mentions of the endoderm germ layer (e.g., “endoderm”).

    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
     will
    -0.07
    ，↵
    -0.07
     ста
    -0.06
     porque
    -0.06
     ακό
    -0.06
     yıl
    -0.06
    OA
    -0.06
    ipop
    -0.06
     pregunta
    -0.06
    POSITIVE LOGITS
    .Companion
    0.07
     Analy
    0.06
     turnovers
    0.06
    _ang
    0.06
    TextWriter
    0.06
    	F
    0.06
    .setVisibility
    0.06
    Helper
    0.06
    Ctrl
    0.06
    .Pass
    0.06
    Activations Density 0.010%

    No Known Activations