© 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. 82224
    Prev
    Next
    INDEX
    Explanations

    file path and directory structure 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
    oretical
    -0.07
    inged
    -0.07
    äºŃ
    -0.07
    Obsolete
    -0.07
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.06
    ãĥ©ãĤ¹
    -0.06
    zel
    -0.06
    -ish
    -0.06
    inth
    -0.06
     Gibbs
    -0.06
    POSITIVE LOGITS
    s
    0.12
    rani
    0.08
    unan
    0.07
    sik
    0.07
    476
    0.07
    ÏĤ
    0.07
    .gwt
    0.07
    a
    0.06
    iado
    0.06
    maal
    0.06
    Activations Density 0.007%

    No Known Activations