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

    Neuronpedia

    APICircuit 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. 5691
    Prev
    Next
    INDEX
    Explanations

    references to identification numbers used in the context of business and taxation

    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
    392
    -0.06
     name
    -0.06
    inh
    -0.06
    yclopedia
    -0.05
    engo
    -0.05
     meaning
    -0.05
     Commentary
    -0.05
    apixel
    -0.05
     nick
    -0.05
    agr
    -0.05
    POSITIVE LOGITS
    assigned
    0.10
    akeup
    0.08
    olean
    0.08
     assigned
    0.07
    acci
    0.07
    SSIP
    0.07
     åĶ
    0.07
     guarante
    0.07
    _assigned
    0.07
    ument
    0.07
    Activations Density 0.006%

    No Known Activations