© 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. 70094
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitions and collaborative projects

    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
    illo
    -0.08
    isz
    -0.08
    ilan
    -0.07
    áct
    -0.07
    agas
    -0.07
    loub
    -0.07
     mesel
    -0.07
    inia
    -0.07
    reon
    -0.07
    lico
    -0.07
    POSITIVE LOGITS
     submissions
    0.09
     challenge
    0.08
     solutions
    0.08
     solution
    0.07
     submission
    0.07
    _submission
    0.07
     submitted
    0.07
     Challenge
    0.06
    glob
    0.06
     ing
    0.06
    Activations Density 0.002%

    No Known Activations