© 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. 9-LLAMASCOPE-RES-131K
    11. 98856
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "spring" and its various forms or implications

    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
    ephir
    -0.09
    .gdx
    -0.07
    ugins
    -0.07
    abyrin
    -0.07
    byss
    -0.07
    ilitation
    -0.07
    enate
    -0.07
    icrous
    -0.07
    anson
    -0.07
    aurus
    -0.07
    POSITIVE LOGITS
    y
    0.09
    -ÑĤаки
    0.08
    ning
    0.08
    à¸ĩาà¸Ļ
    0.08
    steen
    0.07
    -animate
    0.07
    yer
    0.07
    edList
    0.07
    ósito
    0.07
    yb
    0.07
    Activations Density 0.021%

    No Known Activations