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. 5379
    Prev
    Next
    INDEX
    Explanations

    instances of academic research and research topics

    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
    je
    -0.07
    j
    -0.07
    jam
    -0.06
    etag
    -0.06
    uler
    -0.06
    дÑı
    -0.06
    .AutoSizeMode
    -0.06
    orts
    -0.05
    alan
    -0.05
    JE
    -0.05
    POSITIVE LOGITS
    ventus
    0.08
    avy
    0.07
    oyo
    0.07
    Ø´ÙħارÛĮ
    0.07
    orna
    0.07
    implify
    0.07
    ä¹³
    0.07
     Outputs
    0.07
    volution
    0.07
    arella
    0.07
    Activations Density 0.001%

    No Known Activations