© 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. 70313
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Cu" and variations related to 'cucumber'

    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
    ymous
    -0.07
    æ¶
    -0.07
    739
    -0.06
    ASP
    -0.06
    ãĥ¥
    -0.06
    Liv
    -0.06
    orous
    -0.06
    orny
    -0.06
    657
    -0.06
    isci
    -0.06
    POSITIVE LOGITS
    ertino
    0.08
     khẩu
    0.07
    stk
    0.07
    sie
    0.07
    elon
    0.07
    aghan
    0.06
    наÑĢ
    0.06
     cav
    0.06
    xAC
    0.06
    adr
    0.06
    Activations Density 0.023%

    No Known Activations