© 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. 41340
    Prev
    Next
    INDEX
    Explanations

    references to eclipses and related terminology

    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
    士
    -0.08
    IGHL
    -0.08
    eller
    -0.07
    geh
    -0.07
    aclass
    -0.07
    nage
    -0.07
    ubar
    -0.07
    307
    -0.07
    rench
    -0.07
    lis
    -0.07
    POSITIVE LOGITS
    ses
    0.09
    ing
    0.09
    ingly
    0.08
    ory
    0.08
    burg
    0.07
    etti
    0.07
    cion
    0.07
    avy
    0.07
    es
    0.07
    ation
    0.06
    Activations Density 0.004%

    No Known Activations