© 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 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. 88462
    Prev
    Next
    INDEX
    Explanations

    terms related to architectural concepts and elements

    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
    orf
    -0.07
    quot
    -0.06
    785
    -0.06
    pek
    -0.06
    armed
    -0.06
    Ã
    -0.06
    usi
    -0.06
    arine
    -0.06
    zers
    -0.06
    onya
    -0.06
    POSITIVE LOGITS
    itect
    0.10
    ipel
    0.10
    itecture
    0.09
    angel
    0.07
    bishop
    0.07
    etype
    0.07
    ingham
    0.07
    landa
    0.07
    eeper
    0.07
    ẽ
    0.07
    Activations Density 0.014%

    No Known Activations