© 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. 121181
    Prev
    Next
    INDEX
    Explanations

    concepts related to collaboration and teamwork

    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
    ENCHMARK
    -0.08
    TextChanged
    -0.08
    ilig
    -0.08
    -valu
    -0.07
    itez
    -0.07
    odge
    -0.07
    phin
    -0.07
    fout
    -0.07
    ucci
    -0.07
    ÑĢоÑĩ
    -0.07
    POSITIVE LOGITS
     via
    0.08
     with
    0.08
    0.06
    760
    0.06
    finder
    0.06
     ins
    0.06
     in
    0.06
     Guill
    0.06
     for
    0.06
     at
    0.06
    Activations Density 0.025%

    No Known Activations