© 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. 75569
    Prev
    Next
    INDEX
    Explanations

    proper nouns and organizational 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
     ба
    -0.06
     bibli
    -0.06
     Pump
    -0.06
     ÑģовеÑĤ
    -0.05
    achuset
    -0.05
    achat
    -0.05
    stown
    -0.05
     ê³µê°ľ
    -0.05
     pods
    -0.05
    ik
    -0.05
    POSITIVE LOGITS
     news
    0.09
    news
    0.09
    丶
    0.08
     dispatch
    0.08
    -news
    0.08
     ob
    0.07
     News
    0.07
    -wsj
    0.07
    News
    0.07
    _news
    0.07
    Activations Density 0.070%

    No Known Activations