© 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. 59530
    Prev
    Next
    INDEX
    Explanations

    terms related to compression processes and technologies

    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
    ä»ĺãģij
    -0.07
    rol
    -0.07
    anger
    -0.07
    rops
    -0.07
    perature
    -0.07
    icense
    -0.07
    uk
    -0.07
    ibaba
    -0.07
    tsy
    -0.06
    jet
    -0.06
    POSITIVE LOGITS
    ible
    0.09
    ions
    0.09
    ors
    0.09
    edList
    0.08
    edImage
    0.08
    缩
    0.07
    (es
    0.07
    /stretch
    0.07
    ingly
    0.07
    sed
    0.07
    Activations Density 0.005%

    No Known Activations