© 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. 58994
    Prev
    Next
    INDEX
    Explanations

    technical specifications and compatibility information related to software and hardware systems

    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
    otos
    -0.07
    ars
    -0.07
    alto
    -0.06
    fi
    -0.06
    aton
    -0.06
    onte
    -0.06
    OTO
    -0.06
    ÑĥлÑİ
    -0.06
    bib
    -0.06
    ito
    -0.06
    POSITIVE LOGITS
    zik
    0.07
    spd
    0.07
    Compat
    0.07
    åĮħæĭ¬
    0.07
     compatible
    0.07
     provided
    0.07
     compatibility
    0.07
     nhá»Ŀ
    0.07
    æĽ
    0.06
    );$
    0.06
    Activations Density 0.029%

    No Known Activations