© 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. 87225
    Prev
    Next
    INDEX
    Explanations

    scheduled events and discussions

    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
    .ul
    -0.07
    ä»ķ
    -0.06
     YÃĸ
    -0.06
    Serve
    -0.06
    ñana
    -0.06
    -columns
    -0.06
    loo
    -0.06
     Woche
    -0.06
    istring
    -0.06
     иÑģ
    -0.06
    POSITIVE LOGITS
     discussion
    0.09
     discuss
    0.08
     talk
    0.08
     followed
    0.07
     will
    0.07
    discussion
    0.07
    otal
    0.06
    ä¼ļ
    0.06
    erner
    0.06
    DMI
    0.06
    Activations Density 0.024%

    No Known Activations