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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78297
    Prev
    Next
    INDEX
    Explanations

    promotions or giveaways

    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
    ekyll
    -0.07
    ebo
    -0.07
    æij
    -0.07
    astle
    -0.07
    æĮĩæķ°
    -0.07
     exponent
    -0.06
    uchos
    -0.06
    reon
    -0.06
    ż
    -0.06
    roys
    -0.06
    POSITIVE LOGITS
     contest
    0.15
     prize
    0.14
     prizes
    0.13
     contests
    0.13
     Contest
    0.12
     sweep
    0.12
     win
    0.12
     Prize
    0.12
     Sweep
    0.11
     winners
    0.11
    Activations Density 0.171%

    No Known Activations