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

    Neuronpedia

    Jacobian LensNEW
    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. 93764
    Prev
    Next
    INDEX
    Explanations

    dates and chronological 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
    ï½¢
    -0.07
     vá»įng
    -0.07
     masters
    -0.07
     èĹ
    -0.06
     Ary
    -0.06
    à¥ĩà¤Ĥ।
    -0.06
     Eb
    -0.06
    .Abstract
    -0.06
    utas
    -0.06
    ENUM
    -0.06
    POSITIVE LOGITS
    orig
    0.08
    acht
    0.07
    implify
    0.07
     famously
    0.07
    ymes
    0.07
    ì§ľ
    0.07
    ricks
    0.06
    ilden
    0.06
    odia
    0.06
    AuthGuard
    0.06
    Activations Density 0.046%

    No Known Activations