© 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. 57027
    Prev
    Next
    INDEX
    Explanations

    references to biological classifications and taxonomy

    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
    ogg
    -0.08
    igne
    -0.08
    iginal
    -0.07
    iler
    -0.07
    ogui
    -0.07
    imore
    -0.07
    undy
    -0.07
    420
    -0.07
    porto
    -0.07
    eg
    -0.07
    POSITIVE LOGITS
     class
    0.07
     concern
    0.06
     Bair
    0.06
    yx
    0.06
    VERR
    0.06
    Sdk
    0.06
     án
    0.06
     subclass
    0.05
    à¸Īำ
    0.05
     tod
    0.05
    Activations Density 0.003%

    No Known Activations