© 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. 88273
    Prev
    Next
    INDEX
    Explanations

    references to organizing events and committees related to major cultural or sporting occasions

    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
     Worm
    -0.06
    .Members
    -0.06
    (MPI
    -0.06
     ($.
    -0.06
    ACEMENT
    -0.06
    WithOptions
    -0.06
    vero
    -0.06
    »
    -0.06
     DISCLAIMER
    -0.06
    worm
    -0.05
    POSITIVE LOGITS
     Games
    0.08
     Olympics
    0.08
     Olympic
    0.08
    ixo
    0.07
    Games
    0.07
    enthal
    0.07
     ubyt
    0.07
    åĬ
    0.07
    uell
    0.07
    event
    0.07
    Activations Density 0.010%

    No Known Activations