© 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. 39448
    Prev
    Next
    INDEX
    Explanations

    text that includes references to places or geographical features

    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
    Calibri
    -0.09
    instanc
    -0.08
    ãĥ³ãĥij
    -0.08
    strup
    -0.08
     âĹĦ
    -0.07
    acades
    -0.07
    大åħ¨
    -0.07
    ipay
    -0.07
    aped
    -0.07
    gmt
    -0.07
    POSITIVE LOGITS
     pie
    0.06
    Figure
    0.06
    figure
    0.06
     tarn
    0.06
     tele
    0.06
     PIE
    0.06
    Pie
    0.06
    åĮº
    0.06
     demographic
    0.06
    IMS
    0.05
    Activations Density 0.009%

    No Known Activations