© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88207
    Prev
    Next
    INDEX
    Explanations

    references to authors and publication details

    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
     ç¯
    -0.07
    лÑĥб
    -0.07
     Mev
    -0.06
    .Std
    -0.06
    cript
    -0.06
     Heap
    -0.06
    akespeare
    -0.06
    .sy
    -0.06
    attery
    -0.06
    ãĤ¤ãĥĦ
    -0.06
    POSITIVE LOGITS
    uis
    0.07
     jadx
    0.07
    endon
    0.07
    uzzi
    0.07
    aram
    0.07
    unga
    0.07
    agar
    0.07
     seins
    0.06
    ilha
    0.06
    jal
    0.06
    Activations Density 0.060%

    No Known Activations