© 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. 39049
    Prev
    Next
    INDEX
    Explanations

    mentions of contributors and sources in news articles

    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
    inator
    -0.07
    313
    -0.06
     fri
    -0.06
     masa
    -0.06
    ĥ
    -0.06
    ienne
    -0.06
     du
    -0.05
    ç´Ķ
    -0.05
    aqu
    -0.05
     mand
    -0.05
    POSITIVE LOGITS
     contributed
    0.09
     contribution
    0.08
    contributors
    0.07
     addCriterion
    0.07
     contributing
    0.07
     contribute
    0.07
    contrib
    0.07
     Contribution
    0.07
     contributions
    0.07
     Autof
    0.07
    Activations Density 0.006%

    No Known Activations