© 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. 130620
    Prev
    Next
    INDEX
    Explanations

    financial data and 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
    cplusplus
    -0.07
    ollar
    -0.07
    empo
    -0.06
    _verbose
    -0.06
    ause
    -0.06
    DBG
    -0.06
     Lage
    -0.06
     redund
    -0.06
    dda
    -0.06
    ech
    -0.06
    POSITIVE LOGITS
     --------↵
    0.06
    cer
    0.06
    ÑĢади
    0.06
    institution
    0.06
    ãĥ³ãĥĢ
    0.06
    None
    0.06
     ?↵
    0.06
    jer
    0.06
    .scalablytyped
    0.06
    none
    0.06
    Activations Density 0.062%

    No Known Activations