© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22-LLAMASCOPE-RES-131K
    11. 4034
    Prev
    Next
    INDEX
    Explanations

    variations of the word "gondola."

    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
    _TRACE
    -0.08
    оÑıн
    -0.08
    DRV
    -0.08
    uations
    -0.07
    AKE
    -0.07
    inke
    -0.07
    à¤ķरण
    -0.07
    ccione
    -0.07
    /***/
    -0.07
    (æĹ¥
    -0.07
    POSITIVE LOGITS
    olas
    0.09
    ola
    0.08
    oline
    0.08
     g
    0.06
    ole
    0.06
     Gallup
    0.06
    ors
    0.06
    Aspect
    0.06
    oret
    0.06
    ulf
    0.06
    Activations Density 0.001%

    No Known Activations