© 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. 27397
    Prev
    Next
    INDEX
    Explanations

    structural elements in programming 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
    lage
    -0.07
    trace
    -0.06
     Auss
    -0.06
    beg
    -0.06
     Wagner
    -0.06
    mares
    -0.06
    urement
    -0.06
    auss
    -0.06
     Haut
    -0.06
    inee
    -0.06
    POSITIVE LOGITS
    -ra
    0.06
     ÅĻÃŃj
    0.06
    dra
    0.06
     Franco
    0.06
    åłĤ
    0.06
    ấm
    0.06
    ajs
    0.06
     rings
    0.06
     lap
    0.06
    Ķ
    0.06
    Activations Density 0.011%

    No Known Activations