© 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. 15-LLAMASCOPE-RES-131K
    11. 88096
    Prev
    Next
    INDEX
    Explanations

    structured data references and logging outputs related to processes and sessions

    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
    eydi
    -0.07
     Ging
    -0.06
    loom
    -0.06
    bable
    -0.06
    gang
    -0.06
    aeda
    -0.06
     fact
    -0.06
     gang
    -0.06
    eros
    -0.06
     graft
    -0.06
    POSITIVE LOGITS
    -widgets
    0.07
    éĻĨ
    0.07
    uis
    0.07
    UNDLE
    0.07
    mani
    0.06
    odore
    0.06
    URLException
    0.06
     Bounty
    0.06
    Chunk
    0.06
    bundle
    0.06
    Activations Density 0.001%

    No Known Activations