© 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. 128493
    Prev
    Next
    INDEX
    Explanations

    references to claims or numbered procedures within technical descriptions

    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
    ObjectContext
    -0.06
    lesia
    -0.06
     delt
    -0.06
    lé
    -0.06
    amu
    -0.06
    ai
    -0.06
    olla
    -0.06
    èĽ
    -0.06
    warts
    -0.06
    ä½µ
    -0.06
    POSITIVE LOGITS
    éry
    0.07
    celik
    0.07
    eries
    0.07
    ervas
    0.06
    ery
    0.06
    ERY
    0.06
    ViewInit
    0.06
    roller
    0.06
    orthand
    0.06
    alers
    0.06
    Activations Density 0.003%

    No Known Activations