© 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. 87498
    Prev
    Next
    INDEX
    Explanations

    references to social media activity and statements

    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
    -Origin
    -0.08
    oser
    -0.07
    furt
    -0.07
    mazon
    -0.07
    óz
    -0.07
    aset
    -0.07
    catid
    -0.07
     Kostenlose
    -0.06
    .gmail
    -0.06
     gridColumn
    -0.06
    POSITIVE LOGITS
     tweet
    0.11
     tweeted
    0.09
     @
    0.09
     (@
    0.08
    âĢı
    0.08
     posted
    0.08
    tweet
    0.08
     posts
    0.08
    "@
    0.08
     Tweet
    0.07
    Activations Density 0.048%

    No Known Activations