© 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. 6207
    Prev
    Next
    INDEX
    Explanations

    Digits

    np_max-act · gemini-2.0-flash

    technical terms and structures related to programming and API documentation.

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

    the neuron detects alphanumeric identifier tokens that include a numeric index (e.g. hardware or data names like DE1, Link2, SDI1, ADC1, DSI0, EQ2, clkreq_pin[0], etc.)

    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
     ench
    -0.07
     genom
    -0.07
    ginas
    -0.06
    (comp
    -0.06
     financed
    -0.06
     PPP
    -0.06
     グ
    -0.06
     listened
    -0.06
     myš
    -0.06
    ONTAL
    -0.06
    POSITIVE LOGITS
    5
    0.15
    1
    0.14
    4
    0.13
    2
    0.13
    0
    0.12
    3
    0.12
    6
    0.12
    7
    0.10
    五
    0.10
    9
    0.10
    Activations Density 0.246%

    No Known Activations