© 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. 79865
    Prev
    Next
    INDEX
    Explanations

    phrases expressing statistical percentages and related values

    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
    оÑĥ
    -0.07
    -hole
    -0.06
    hole
    -0.06
    lox
    -0.06
     Epid
    -0.06
     rack
    -0.06
    bild
    -0.06
    bridge
    -0.06
     Ep
    -0.06
     racks
    -0.06
    POSITIVE LOGITS
    aurus
    0.07
    以ä¸Ĭ
    0.07
    quisite
    0.06
    -plus
    0.06
    altimore
    0.06
    æ¯
    0.06
    ailer
    0.06
    tplib
    0.06
    elts
    0.06
    ãĤ·ãĤ¢
    0.06
    Activations Density 0.016%

    No Known Activations