© 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. 80112
    Prev
    Next
    INDEX
    Explanations

    mathematical theorems and references

    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
    ICA
    -0.08
     recess
    -0.07
    iers
    -0.06
    icer
    -0.06
    deaux
    -0.06
    uppe
    -0.06
    èįī
    -0.06
    anut
    -0.06
    .nano
    -0.06
    hani
    -0.06
    POSITIVE LOGITS
    rikes
    0.07
     gu
    0.07
     below
    0.06
    Ñħо
    0.06
     Edison
    0.06
    Dlg
    0.06
    ivre
    0.06
    isle
    0.06
    oose
    0.06
    ãĥ³ãĤ¬
    0.06
    Activations Density 0.121%

    No Known Activations