© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87928
    Prev
    Next
    INDEX
    Explanations

    elements related to seasonal culinary experiences and restaurant offerings

    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
    моÑĢ
    -0.07
     Sist
    -0.06
    ouri
    -0.06
     basically
    -0.06
    tgt
    -0.06
    UNDLE
    -0.06
    pleasant
    -0.06
    гл
    -0.06
     decent
    -0.06
    WithOptions
    -0.06
    POSITIVE LOGITS
    azio
    0.07
    daily
    0.07
     daily
    0.06
    ich
    0.06
    aben
    0.06
     ICMP
    0.06
     Tribe
    0.06
    ãĤĿ
    0.06
     travellers
    0.06
     TRUE
    0.06
    Activations Density 0.013%

    No Known Activations