© 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. 56410
    Prev
    Next
    INDEX
    Explanations

    significant political events and reforms

    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
    reh
    -0.08
    ppo
    -0.07
     unconventional
    -0.07
    rei
    -0.07
    arto
    -0.06
     gaze
    -0.06
     sovereign
    -0.06
    asher
    -0.06
    rette
    -0.06
    unik
    -0.06
    POSITIVE LOGITS
    .Begin
    0.06
     Clement
    0.06
     alien
    0.06
    èĢĢ
    0.06
     reels
    0.06
    Castle
    0.06
    积
    0.06
    ESA
    0.06
     SaÄŁ
    0.06
    alcon
    0.05
    Activations Density 0.025%

    No Known Activations