© 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. 38954
    Prev
    Next
    INDEX
    Explanations

    references to community engagement and social justice activities

    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
     noc
    -0.06
    odesk
    -0.06
    jee
    -0.06
    abad
    -0.06
     wasted
    -0.06
     Kaplan
    -0.06
    ogenerated
    -0.05
    qli
    -0.05
    YTE
    -0.05
     Tweets
    -0.05
    POSITIVE LOGITS
    isle
    0.07
    _iff
    0.07
     our
    0.07
    sville
    0.07
    our
    0.07
    .scalablytyped
    0.06
    Recorder
    0.06
     naše
    0.06
     unseren
    0.06
     ours
    0.06
    Activations Density 0.009%

    No Known Activations