© 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. 119455
    Prev
    Next
    INDEX
    Explanations

    numerical stats and scores related to competitions or games

    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
    ovu
    -0.07
    IMITIVE
    -0.07
    大åħ¨
    -0.07
    egie
    -0.07
    zburg
    -0.07
    ariat
    -0.07
    Åĵ
    -0.07
    uur
    -0.06
    icum
    -0.06
    elerik
    -0.06
    POSITIVE LOGITS
     Alv
    0.07
    udd
    0.07
    izu
    0.06
     centrally
    0.06
    ä¸
    0.06
    oret
    0.06
     Mej
    0.06
    sch
    0.06
    bottom
    0.06
    æ·
    0.06
    Activations Density 0.001%

    No Known Activations