© 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. 128536
    Prev
    Next
    INDEX
    Explanations

    speed

    np_max-act · gemini-2.0-flash

    technical terms related to high-speed data transmission and switching devices.

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

    The neuron responds to technical specification phrases, especially high-speed or network performance terms (e.g. “high-speed,” “real-time,” “Local Area Network”).

    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
     altında
    -0.07
    てい
    -0.07
     bất
    -0.07
    了一
    -0.07
    _BEFORE
    -0.07
    、三
    -0.07
    ("@
    -0.06
    -tw
    -0.06
    (LP
    -0.06
    ався
    -0.06
    POSITIVE LOGITS
     pense
    0.07
     Speedway
    0.06
     vergi
    0.06
     controvers
    0.06
    rate
    0.06
     longtime
    0.06
     ASF
    0.06
    Š
    0.06
    Expr
    0.06
    FU
    0.06
    Activations Density 0.127%

    No Known Activations