© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 129670
    Prev
    Next
    INDEX
    Explanations

    references to concerts and musical performances

    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
    ernaut
    -0.07
    è¾°
    -0.07
    ierz
    -0.07
    lessness
    -0.07
    aley
    -0.07
    outu
    -0.07
    bau
    -0.07
    NING
    -0.06
    ball
    -0.06
    /chart
    -0.06
    POSITIVE LOGITS
    ito
    0.07
     Learned
    0.07
    ez
    0.06
    e
    0.06
    889
    0.06
    etter
    0.06
    edly
    0.06
    ue
    0.06
    ado
    0.06
    887
    0.06
    Activations Density 0.004%

    No Known Activations