© 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. 4960
    Prev
    Next
    INDEX
    Explanations

    references to stretching or flexible materials 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
    InstanceOf
    -0.08
    adam
    -0.07
    ÑģÑĮ
    -0.07
    ÑŁ
    -0.07
    emie
    -0.07
    brahim
    -0.06
    WithPath
    -0.06
    oling
    -0.06
    cheng
    -0.06
    anders
    -0.06
    POSITIVE LOGITS
    /stretch
    0.09
    ToFit
    0.08
     Stretch
    0.08
    y
    0.07
    combe
    0.07
    neck
    0.07
    uhl
    0.07
    Stretch
    0.07
    (es
    0.07
    -neck
    0.07
    Activations Density 0.008%

    No Known Activations