© 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. 4112
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those related to statistics 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
    299
    -0.06
     fewer
    -0.06
    usch
    -0.06
    apel
    -0.06
    islav
    -0.06
    vis
    -0.06
     lam
    -0.06
    çļĦä¸Ģ
    -0.06
    .tc
    -0.06
     Chun
    -0.06
    POSITIVE LOGITS
    istringstream
    0.07
    idade
    0.07
    -sized
    0.07
    .extensions
    0.07
    -haired
    0.07
    oundingBox
    0.07
     haired
    0.07
    unger
    0.06
    icable
    0.06
     vững
    0.06
    Activations Density 0.037%

    No Known Activations