© 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. 62860
    Prev
    Next
    INDEX
    Explanations

    expressions of joy or satisfaction

    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
    wear
    -0.07
    oko
    -0.07
    ww
    -0.07
    ali
    -0.06
    592
    -0.06
    nt
    -0.06
    _RESOLUTION
    -0.06
    ps
    -0.06
    af
    -0.06
    àµįà´
    -0.06
    POSITIVE LOGITS
    leck
    0.09
    mente
    0.08
    ecast
    0.08
    indir
    0.07
    lator
    0.07
    egov
    0.07
    utor
    0.07
    strand
    0.07
    yte
    0.07
    addOn
    0.07
    Activations Density 0.006%

    No Known Activations