© 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. 76248
    Prev
    Next
    INDEX
    Explanations

    fractions, measurements, or numeric values related to cooking or crafting

    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
    y
    -0.06
     Iso
    -0.06
    bang
    -0.06
    tar
    -0.06
    recated
    -0.06
     Mall
    -0.06
    اب
    -0.06
    toast
    -0.06
    Latch
    -0.06
    otify
    -0.06
    POSITIVE LOGITS
    à¥ĭषण
    0.07
    aken
    0.06
    OKIE
    0.06
    abra
    0.06
    ction
    0.06
     Shields
    0.06
    ÑįÑĤомÑĥ
    0.06
    OnError
    0.06
    _cre
    0.06
    wayne
    0.05
    Activations Density 0.018%

    No Known Activations