© 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. 27330
    Prev
    Next
    INDEX
    Explanations

    segments of code or script 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
    彦
    -0.07
    attle
    -0.07
    illac
    -0.07
     Deploy
    -0.07
     Copenhagen
    -0.06
    ittings
    -0.06
    ÑĢÑĥд
    -0.06
     Helsinki
    -0.06
    -ng
    -0.06
    warf
    -0.06
    POSITIVE LOGITS
    QC
    0.08
    .MixedReality
    0.07
    essed
    0.07
    ASP
    0.07
    /umd
    0.07
     dish
    0.07
    /locale
    0.07
     Survivor
    0.06
    ibly
    0.06
    Labor
    0.06
    Activations Density 0.001%

    No Known Activations