© 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. 15-LLAMASCOPE-RES-131K
    11. 89247
    Prev
    Next
    INDEX
    Explanations

    terms related to technology infrastructure and security

    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
    ano
    -0.07
    .SingleOrDefault
    -0.07
     Tate
    -0.07
    ymax
    -0.07
    .gwt
    -0.06
    гов
    -0.06
    éric
    -0.06
    اØ
    -0.06
    /apis
    -0.06
    ulin
    -0.06
    POSITIVE LOGITS
     haystack
    0.07
    juven
    0.06
    oola
    0.06
    inka
    0.06
    夫
    0.06
    acam
    0.06
    iani
    0.06
     Herrera
    0.06
    CMP
    0.06
    needle
    0.06
    Activations Density 0.008%

    No Known Activations