© 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. 40357
    Prev
    Next
    INDEX
    Explanations

    dates and availability of events or updates

    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
    andi
    -0.07
     COMMENTS
    -0.06
     Loose
    -0.06
    é¨
    -0.06
     Moran
    -0.06
    fsp
    -0.06
    etter
    -0.06
    loyd
    -0.06
     AssemblyVersion
    -0.06
    æĪ²
    -0.06
    POSITIVE LOGITS
    chio
    0.08
    áf
    0.07
    pill
    0.07
    apus
    0.07
    Merit
    0.06
    ingleton
    0.06
    ushi
    0.06
    servers
    0.06
    åij¨
    0.06
    ikel
    0.06
    Activations Density 0.001%

    No Known Activations