© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127840
    Prev
    Next
    INDEX
    Explanations

    questions about accessibility and support for individuals in various contexts

    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
     दर
    -0.07
     exh
    -0.06
    opl
    -0.06
    ENAME
    -0.06
    amp
    -0.06
     tackle
    -0.06
    Minus
    -0.06
    ë³µ
    -0.06
    ghan
    -0.06
    cket
    -0.06
    POSITIVE LOGITS
    олÑİ
    0.07
     UIStoryboard
    0.06
    uelles
    0.06
    777
    0.06
    ITTER
    0.06
    emet
    0.06
    .Areas
    0.06
    åĥį
    0.06
    -pocket
    0.06
     living
    0.06
    Activations Density 0.028%

    No Known Activations