© 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. 54222
    Prev
    Next
    INDEX
    Explanations

    textual elements indicating summaries or key points

    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
    hiro
    -0.08
    ctors
    -0.06
    556
    -0.06
    ween
    -0.06
    omid
    -0.06
    IVED
    -0.06
    hi
    -0.06
    ká
    -0.06
    ά
    -0.06
    ика
    -0.06
    POSITIVE LOGITS
     why
    0.09
     how
    0.08
    ä¸Ģç§į
    0.07
     what
    0.07
    rescia
    0.07
     implications
    0.07
    vox
    0.07
    fld
    0.06
    GF
    0.06
    ynthia
    0.06
    Activations Density 0.031%

    No Known Activations