© 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 EvalsExportsinterp-engineNEWAPI 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. 27927
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming instructions

    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
    izza
    -0.08
    enville
    -0.07
    lords
    -0.07
    auc
    -0.07
    prü
    -0.07
    ornado
    -0.06
    mlin
    -0.06
     another
    -0.06
    éĤ£
    -0.06
    head
    -0.06
    POSITIVE LOGITS
     ):↵
    0.08
     :↵↵
    0.08
    ):↵
    0.07
     Note
    0.07
     ):↵↵
    0.07
    ":↵
    0.07
    ():↵↵
    0.07
    :↵↵↵
    0.07
     :↵
    0.07
    ijk
    0.07
    Activations Density 0.024%

    No Known Activations