© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 88231
    Prev
    Next
    INDEX
    Explanations

    terms related to emerging or developing concepts and individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    tabs
    -0.07
     Cousins
    -0.07
    egral
    -0.07
    auen
    -0.07
    sp
    -0.06
    erts
    -0.06
    raj
    -0.06
    ray
    -0.06
    %M
    -0.06
    алеж
    -0.06
    POSITIVE LOGITS
    cola
    0.07
    ently
    0.07
    ksen
    0.07
    utut
    0.07
    uder
    0.06
    ffen
    0.06
    ëĵľë¦¬
    0.06
    ipple
    0.06
     Gund
    0.06
    GENCY
    0.06
    Activations Density 0.006%

    No Known Activations