© 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. 15-LLAMASCOPE-RES-131K
    6. 104284
    Prev
    Next
    INDEX
    Explanations

    action verbs related to creative and production activities

    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
    ccione
    -0.07
    Ŀ
    -0.06
    /by
    -0.06
    implify
    -0.06
    Ł
    -0.06
    antz
    -0.06
    خصÙĪØµ
    -0.06
    ivent
    -0.06
    raud
    -0.06
    starter
    -0.06
    POSITIVE LOGITS
     another
    0.12
     two
    0.10
    another
    0.10
     several
    0.10
     three
    0.08
     Another
    0.07
    Another
    0.07
    two
    0.07
     twice
    0.07
    两个
    0.07
    Activations Density 0.017%

    No Known Activations