© 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. 81019
    Prev
    Next
    INDEX
    Explanations

    quantifiable data or statistics related to measurements and percentages

    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
    ubb
    -0.07
    aven
    -0.07
    oundary
    -0.06
     Testament
    -0.06
     cust
    -0.06
    itz
    -0.06
    ça
    -0.06
    /pm
    -0.06
    erie
    -0.06
    intl
    -0.06
    POSITIVE LOGITS
    ively
    0.07
    aln
    0.07
    uous
    0.07
    vala
    0.07
    eza
    0.06
    vir
    0.06
    th
    0.06
    ména
    0.06
    erv
    0.06
    spiel
    0.06
    Activations Density 0.042%

    No Known Activations