© 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. 30609
    Prev
    Next
    INDEX
    Explanations

    programming constructs and variables in code snippets

    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
    Äįet
    -0.08
    ̧
    -0.07
    holm
    -0.07
    ¶Į
    -0.07
    reich
    -0.07
    رÙĬÙħ
    -0.07
    ære
    -0.07
    รวม
    -0.07
    '].$
    -0.07
    ATAB
    -0.07
    POSITIVE LOGITS
     "
    0.16
    ="
    0.12
    ("
    0.11
     “
    0.10
     «
    0.09
    ãĢĮ
    0.08
     "-
    0.08
    ["
    0.08
     \"
    0.08
     ``
    0.07
    Activations Density 0.097%

    No Known Activations