© 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. 77195
    Prev
    Next
    INDEX
    Explanations

    function definitions and their syntax in code

    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
    als
    -0.06
    abin
    -0.06
    ĺìĿ´
    -0.06
     dü
    -0.06
    etal
    -0.06
    HING
    -0.06
    ema
    -0.06
    çĿ£
    -0.06
     Bool
    -0.05
    طر
    -0.05
    POSITIVE LOGITS
    benh
    0.07
    OffsetTable
    0.07
    ataire
    0.07
    /Dk
    0.07
    :frame
    0.07
    =edge
    0.07
     "(\<
    0.07
    olle
    0.07
    arness
    0.06
    è»
    0.06
    Activations Density 0.001%

    No Known Activations