© 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. 17-LLAMASCOPE-RES-131K
    6. 78671
    Prev
    Next
    INDEX
    Explanations

    quotation marks or phrases often associated with quotations

    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
    iale
    -0.07
    ãĤ¦ãĥĪ
    -0.07
    лÑĸд
    -0.07
    uyla
    -0.07
    icate
    -0.07
    á»ķng
    -0.07
    SPELL
    -0.07
    اÙħÛĮ
    -0.06
    iate
    -0.06
    empl
    -0.06
    POSITIVE LOGITS
    Muon
    0.06
    xfff
    0.06
    eded
    0.06
    graded
    0.06
     previous
    0.06
    -reply
    0.06
    âķĿ
    0.06
     Reply
    0.06
    verse
    0.06
    adero
    0.06
    Activations Density 0.004%

    No Known Activations