© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89941
    Prev
    Next
    INDEX
    Explanations

    phrases related to wildlife and nature

    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
     jungle
    -0.07
    dex
    -0.07
    iano
    -0.07
    ungle
    -0.06
    eah
    -0.06
    ewood
    -0.06
    xit
    -0.06
    racak
    -0.06
     climbing
    -0.06
     spiders
    -0.06
    POSITIVE LOGITS
     Wings
    0.09
     Swan
    0.08
     bird
    0.08
     water
    0.08
     wings
    0.08
    -wing
    0.08
    ifu
    0.08
    åĺ´
    0.07
     flock
    0.07
     birds
    0.07
    Activations Density 0.006%

    No Known Activations