© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 108428
    Prev
    Next
    INDEX
    Explanations

    words with specific phonetic or morphological patterns

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

    The highlighted tokens are fragments or parts of names (people, places, products, terms) that appear in various contexts such as academic citations, geographical locations, product descriptions, and professional titles.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.09
    lov
    -0.08
    illions
    -0.08
    ler
    -0.08
    bla
    -0.07
    меÑĩ
    -0.07
    baseUrl
    -0.07
    stdcall
    -0.07
    blast
    -0.07
    _hz
    -0.07
    POSITIVE LOGITS
    abeth
    0.11
    ator
    0.07
    ka
    0.07
    sch
    0.06
    an
    0.06
    abet
    0.06
    wood
    0.06
     Datum
    0.05
    ta
    0.05
    enus
    0.05
    Activations Density 0.036%

    No Known Activations