© 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. 60448
    Prev
    Next
    INDEX
    Explanations

    quantitative assessments related to health and performance metrics

    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
    essim
    -0.06
    rn
    -0.06
    ett
    -0.06
     inter
    -0.06
    eyin
    -0.06
    rosso
    -0.06
     Funds
    -0.06
    bage
    -0.06
    erture
    -0.06
    æĸŃ
    -0.06
    POSITIVE LOGITS
     damage
    0.07
    ãĥªãĥ¼
    0.07
    kv
    0.06
    ضÙħ
    0.06
    -INF
    0.06
    .hits
    0.06
     sơ
    0.06
    rikes
    0.06
     Lloyd
    0.06
    å§Ĩ
    0.06
    Activations Density 0.006%

    No Known Activations