© 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. 72807
    Prev
    Next
    INDEX
    Explanations

    references to the concept of grace

    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
    hausen
    -0.08
    chte
    -0.08
    매
    -0.07
    laz
    -0.07
    regation
    -0.07
    ltra
    -0.07
    (*)(
    -0.07
    tin
    -0.07
    ạt
    -0.07
    region
    -0.07
    POSITIVE LOGITS
    fully
    0.12
    ful
    0.11
    fulness
    0.09
    ffa
    0.09
    full
    0.09
    ably
    0.08
    FUL
    0.08
    less
    0.07
    ually
    0.07
    ient
    0.07
    Activations Density 0.005%

    No Known Activations