© 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. 59181
    Prev
    Next
    INDEX
    Explanations

    references to official or governmental contexts

    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
    iese
    -0.08
    ziej
    -0.07
    bsite
    -0.06
    ÌĨ
    -0.06
    essler
    -0.06
     Tomorrow
    -0.06
    ypi
    -0.06
    iggers
    -0.06
    žit
    -0.06
    Äĩ
    -0.06
    POSITIVE LOGITS
    shima
    0.07
    gen
    0.07
    onymous
    0.06
    847
    0.06
    scribe
    0.06
     Genius
    0.06
     bid
    0.06
    bij
    0.06
     cél
    0.06
    лиÑĤ
    0.06
    Activations Density 0.012%

    No Known Activations