© 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. 87569
    Prev
    Next
    INDEX
    Explanations

    code structures defined by curly brackets and equal signs

    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
    ntl
    -0.07
    ÄĻż
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    ModelError
    -0.07
    printStats
    -0.06
    Memcpy
    -0.06
    ỹ
    -0.06
    orsk
    -0.06
     Leban
    -0.06
    enberg
    -0.06
    POSITIVE LOGITS
    ses
    0.07
    ENA
    0.07
    LOWER
    0.07
    ammable
    0.06
    su
    0.06
    sil
    0.06
     BASIS
    0.06
     ìķķ
    0.06
     Byl
    0.06
    oint
    0.06
    Activations Density 0.009%

    No Known Activations