© 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. 73604
    Prev
    Next
    INDEX
    Explanations

    mentions of contests and competitive events

    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
    ulin
    -0.08
    onda
    -0.07
    erce
    -0.07
    -0.07
    letcher
    -0.07
    eron
    -0.07
    essian
    -0.07
    ulton
    -0.07
    aret
    -0.07
    inders
    -0.07
    POSITIVE LOGITS
    ions
    0.09
    IONS
    0.08
    ual
    0.08
    ion
    0.08
    uing
    0.07
    ively
    0.07
    ants
    0.07
    ional
    0.07
    ive
    0.07
    osterone
    0.07
    Activations Density 0.008%

    No Known Activations