© 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. 89424
    Prev
    Next
    INDEX
    Explanations

    Documentation

    np_max-act · gemini-2.0-flash

    the use of APIs in Python.

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

    The neuron is activated by floating‐point number tokens (numeric values with digits and a decimal point).

    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
    charted
    -0.06
    	rm
    -0.06
     providedIn
    -0.06
    -te
    -0.06
     genotype
    -0.06
     careg
    -0.06
     Hercules
    -0.05
     시장
    -0.05
     AppModule
    -0.05
    ollen
    -0.05
    POSITIVE LOGITS
    (:,
    0.07
     appoint
    0.07
    %,
    0.06
    (\'
    0.06
    *,
    0.06
    preh
    0.06
    EY
    0.06
     Fridays
    0.06
    .cuda
    0.06
     amnesty
    0.06
    Activations Density 0.018%

    No Known Activations