Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93907
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their achievements in sports 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
    igel
    -0.07
    DCF
    -0.07
    nce
    -0.06
     redeemed
    -0.06
     heartbeat
    -0.06
     Hog
    -0.06
    еле
    -0.06
    ACES
    -0.06
    acr
    -0.06
    empo
    -0.06
    POSITIVE LOGITS
    arella
    0.07
    ossal
    0.07
    alian
    0.07
    ersh
    0.07
    oram
    0.06
    urger
    0.06
     sque
    0.06
    acom
    0.06
    że
    0.06
    erve
    0.06
    Activations Density 0.026%

    No Known Activations