© 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. 31249
    Prev
    Next
    INDEX
    Explanations

    questions relating to personal experiences and creativity in one's career

    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
     Whit
    -0.06
    orney
    -0.06
    iliz
    -0.06
    ÑĢива
    -0.06
     <<-
    -0.06
    roupon
    -0.06
    ãĥ¼ãĥ³
    -0.06
     Jiang
    -0.06
     Patel
    -0.05
     chiá»ģu
    -0.05
    POSITIVE LOGITS
    rite
    0.07
    /or
    0.06
    æĪĸ
    0.06
    oreach
    0.06
    avicon
    0.06
     hâl
    0.06
    alars
    0.06
    ÐľÐŀ
    0.06
     chall
    0.06
    ocoder
    0.06
    Activations Density 0.030%

    No Known Activations