© 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. 107563
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and concepts

    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
    ushi
    -0.07
    кÑĥл
    -0.07
    chemas
    -0.07
    GLOBALS
    -0.07
    achment
    -0.07
    otta
    -0.06
    lej
    -0.06
    _TRUNC
    -0.06
    lobals
    -0.06
    atcher
    -0.06
    POSITIVE LOGITS
    ness
    0.07
    éij
    0.07
    ify
    0.07
    awk
    0.06
    ãģªãĤĭ
    0.06
    ulo
    0.06
    ric
    0.06
    ifiable
    0.06
    =yes
    0.06
    LIKELY
    0.06
    Activations Density 0.030%

    No Known Activations