Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 128943
    Prev
    Next
    INDEX
    Explanations

    terms related to winemaking processes and equipment

    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
    ëĬ¥
    -0.08
    kový
    -0.07
    976
    -0.07
    odon
    -0.07
    ovky
    -0.07
    kdir
    -0.07
    steder
    -0.07
    asma
    -0.07
    vely
    -0.07
    esub
    -0.07
    POSITIVE LOGITS
     temperature
    0.07
    ottes
    0.06
     flo
    0.06
     Temperature
    0.06
     ferm
    0.06
     ferment
    0.06
    flo
    0.06
     cann
    0.06
    CELL
    0.05
     prim
    0.05
    Activations Density 0.003%

    No Known Activations