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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87723
    Prev
    Next
    INDEX
    Explanations

    terms related to the production and characteristics of wine and hops

    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
    ritch
    -0.08
    angler
    -0.07
    åĬŀ
    -0.07
    attached
    -0.07
    ozem
    -0.07
    )prepare
    -0.07
    467
    -0.07
    ChangedEventArgs
    -0.07
    ivy
    -0.07
    metics
    -0.07
    POSITIVE LOGITS
     Hardy
    0.07
     DNA
    0.06
     noir
    0.06
     Gim
    0.06
     Noir
    0.06
     varieties
    0.06
     Late
    0.06
     genes
    0.06
     grapes
    0.06
     Sob
    0.05
    Activations Density 0.001%

    No Known Activations