© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 83574
    Prev
    Next
    INDEX
    Explanations

    non-standard characters, symbols, or formatting elements in the text

    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
    tplib
    -0.06
     Angeles
    -0.06
    Ðĥ
    -0.06
    Added
    -0.06
    inee
    -0.06
    apia
    -0.06
    /Dk
    -0.05
     trous
    -0.05
     Added
    -0.05
    887
    -0.05
    POSITIVE LOGITS
    æ¡IJ
    0.09
    tür
    0.07
     neust
    0.07
    ÑĤож
    0.07
    ále
    0.07
    ãĥĸãĥ«
    0.07
     Barbar
    0.07
    ROUGH
    0.07
    ừng
    0.07
    asti
    0.07
    Activations Density 0.089%

    No Known Activations