© 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. 95602
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements related to large populations or statistics

    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
     BATCH
    -0.08
     Batch
    -0.07
    iyat
    -0.06
    basket
    -0.06
     basket
    -0.06
    mant
    -0.06
    ãĤ¸ãĤ¢
    -0.06
    çĤī
    -0.06
    PointerType
    -0.06
    umin
    -0.06
    POSITIVE LOGITS
    htar
    0.08
     Hit
    0.07
    itere
    0.07
     ÑĢÑĥб
    0.06
    Hit
    0.06
    /downloads
    0.06
     dollars
    0.06
    ae
    0.06
     hit
    0.06
    atore
    0.06
    Activations Density 0.043%

    No Known Activations