© 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. 17-LLAMASCOPE-RES-131K
    11. 119225
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and emphasize notions of experience and enjoyment

    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
    ichel
    -0.07
    /apis
    -0.07
    letal
    -0.07
    еÑĢи
    -0.06
    hei
    -0.06
    ÙĪغ
    -0.06
    aidu
    -0.06
    ãĥ³ãĥĢ
    -0.06
    essen
    -0.06
    ircle
    -0.06
    POSITIVE LOGITS
     spending
    0.08
    spent
    0.07
     spend
    0.07
    pac
    0.07
     viewpoint
    0.07
     Blackburn
    0.06
     Spending
    0.06
     spender
    0.06
    æĶ
    0.06
    927
    0.06
    Activations Density 0.000%

    No Known Activations