© 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. 69432
    Prev
    Next
    INDEX
    Explanations

    various types of awards and recognitions in the context of achievements

    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
    ukkit
    -0.07
    andas
    -0.07
    ä¼¼
    -0.07
    ellar
    -0.07
    TypeEnum
    -0.07
    .GroupLayout
    -0.07
     Hai
    -0.06
     Ñģил
    -0.06
    rove
    -0.06
    tvrt
    -0.06
    POSITIVE LOGITS
    cht
    0.06
    amon
    0.06
     scheme
    0.06
     program
    0.06
    154
    0.06
    ãģŁãĤī
    0.06
    354
    0.06
    184
    0.06
    acker
    0.06
    apol
    0.06
    Activations Density 0.038%

    No Known Activations