© 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. 87742
    Prev
    Next
    INDEX
    Explanations

    specific names, terms, and references related to aviation and its community

    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
    uzzi
    -0.09
    ees
    -0.09
    asse
    -0.08
    ech
    -0.07
    eh
    -0.07
    ele
    -0.07
    tır
    -0.07
    tı
    -0.07
    zem
    -0.07
    andal
    -0.07
    POSITIVE LOGITS
    (es
    0.10
    es
    0.09
    mallow
    0.09
    midt
    0.08
    awn
    0.08
    ãĤħ
    0.08
    oulder
    0.08
    ES
    0.08
    rooms
    0.07
    à¥įà¤ļ
    0.07
    Activations Density 0.080%

    No Known Activations