© 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. 87350
    Prev
    Next
    INDEX
    Explanations

    terms related to botany, particularly plant characteristics and classifications

    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
    uchen
    -0.07
     ked
    -0.07
    çīĩ
    -0.07
    .idea
    -0.07
     yok
    -0.07
    amus
    -0.06
    anlı
    -0.06
    _ARCH
    -0.06
    âl
    -0.06
    IBC
    -0.06
    POSITIVE LOGITS
    ness
    0.12
    heid
    0.10
    NESS
    0.10
     ترÛĮÙĨ
    0.09
    âĢĮترÛĮÙĨ
    0.08
     enough
    0.07
    eness
    0.07
    elly
    0.07
    ãģĻãģİ
    0.07
    ement
    0.07
    Activations Density 0.036%

    No Known Activations