© 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. 15-LLAMASCOPE-RES-131K
    11. 87881
    Prev
    Next
    INDEX
    Explanations

    code constructs related to image processing

    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
    olon
    -0.07
    enberg
    -0.07
    mid
    -0.07
    ks
    -0.07
    áv
    -0.06
    ingen
    -0.06
    optera
    -0.06
    mir
    -0.06
    oun
    -0.06
    apers
    -0.06
    POSITIVE LOGITS
     mak
    0.07
     IDD
    0.07
    sizes
    0.06
    reopen
    0.06
    ῶ
    0.06
    UsageId
    0.06
    _warnings
    0.06
     æ©
    0.06
    lobal
    0.06
    >NN
    0.06
    Activations Density 0.013%

    No Known Activations