Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5357
    Prev
    Next
    INDEX
    Explanations

    references to asynchronous programming tasks

    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
    asar
    -0.07
    Ïģο
    -0.06
    icher
    -0.06
    :async
    -0.06
    ±
    -0.06
    ieur
    -0.06
    iod
    -0.06
    390
    -0.06
    igel
    -0.06
    aint
    -0.05
    POSITIVE LOGITS
    echa
    0.07
    "./
    0.07
    toi
    0.07
    icast
    0.07
     ragaz
    0.07
    groupid
    0.07
    gregate
    0.07
    outu
    0.07
    wap
    0.06
    icit
    0.06
    Activations Density 0.000%

    No Known Activations