© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12617
    Prev
    Next
    INDEX
    Explanations

    projection

    np_max-act · gemini-2.0-flash

    This neuron detects terms describing neural anatomical connectivity (e.g. projections, inputs, outputs, afferents/efferents, connections).

    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
     pharmacy
    -0.06
    Ion
    -0.06
    gements
    -0.06
    ANY
    -0.06
     IllegalAccessException
    -0.06
    WER
    -0.06
     recur
    -0.06
     assaulted
    -0.06
     statute
    -0.06
    enha
    -0.06
    POSITIVE LOGITS
     rom
    0.07
     nabíd
    0.07
     đảo
    0.07
     Warning
    0.07
    ินค
    0.07
     podmínky
    0.07
     compuls
    0.06
     %[
    0.06
    τηγορία
    0.06
    �재
    0.06
    Activations Density 0.016%

    No Known Activations