© 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. 81009
    Prev
    Next
    INDEX
    Explanations

    references to protocol buffers

    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
    ÑģÑĥÑĤÑģÑĤв
    -0.07
    iye
    -0.06
    ÏħÏĩ
    -0.06
    夫
    -0.06
    oret
    -0.06
    ÑģÑĥÑĤ
    -0.06
    pared
    -0.06
    ple
    -0.06
    jvu
    -0.06
    ACHI
    -0.06
    POSITIVE LOGITS
    sim
    0.07
    Äįást
    0.06
    ually
    0.06
    byn
    0.06
    IJ
    0.06
    udden
    0.06
    enstein
    0.06
    shortcode
    0.06
     å°
    0.06
     å½
    0.06
    Activations Density 0.000%

    No Known Activations