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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94322
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific notation and references

    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
    osate
    -0.08
     Geile
    -0.08
    Defaults
    -0.07
    .sdk
    -0.07
    ãĤĪãģı
    -0.07
     ÙħØ´
    -0.07
    æݪ
    -0.07
    habi
    -0.07
    áp
    -0.07
     rodin
    -0.07
    POSITIVE LOGITS
     studies
    0.11
     Studies
    0.10
     recently
    0.09
     recent
    0.09
    Studies
    0.08
    recent
    0.08
    iven
    0.06
     Recently
    0.06
    0.06
     published
    0.06
    Activations Density 0.029%

    No Known Activations