© 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. 17-LLAMASCOPE-RES-131K
    11. 58674
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or groups

    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
    igans
    -0.07
    .nih
    -0.07
    edelta
    -0.07
    ë¸
    -0.07
    uario
    -0.07
    iationException
    -0.07
    issement
    -0.07
    ocket
    -0.07
    osloven
    -0.07
    avan
    -0.07
    POSITIVE LOGITS
    ally
    0.07
    o
    0.07
    ild
    0.06
    inds
    0.06
    -called
    0.06
     little
    0.06
     Republic
    0.06
    anic
    0.06
    yer
    0.06
    ¿
    0.06
    Activations Density 0.003%

    No Known Activations