© 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. 9-LLAMASCOPE-RES-131K
    11. 95550
    Prev
    Next
    INDEX
    Explanations

    terms related to flora and vegetation

    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
    ame
    -0.06
    ghest
    -0.06
    ultur
    -0.06
    ustin
    -0.06
    é±¼
    -0.06
    jÄĻ
    -0.06
    ifen
    -0.06
    ialect
    -0.06
    ond
    -0.06
    éĻ
    -0.05
    POSITIVE LOGITS
    _fwd
    0.07
     Sachs
    0.07
    -transitional
    0.07
     Crowley
    0.06
    koneksi
    0.06
     Soph
    0.06
    ãĤ¥
    0.06
    ãģ¯ãģļ
    0.06
     Shir
    0.06
    arie
    0.06
    Activations Density 0.009%

    No Known Activations