© 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. 79689
    Prev
    Next
    INDEX
    Explanations

    key statistics and achievements related to a specific athlete'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
    aleb
    -0.08
     Äijang
    -0.08
    æŃ£åľ¨
    -0.07
     newest
    -0.07
     recent
    -0.07
    æĺ¨
    -0.07
    olib
    -0.07
     âĹĦ
    -0.07
     lately
    -0.07
    缮åīį
    -0.07
    POSITIVE LOGITS
    197
    0.07
     contempor
    0.07
     era
    0.06
    idget
    0.06
    -era
    0.06
     induction
    0.06
    ood
    0.06
     retire
    0.06
     career
    0.06
    198
    0.06
    Activations Density 0.021%

    No Known Activations