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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5144
    Prev
    Next
    INDEX
    Explanations

    specific historical references and names associated with Native American tribes and cultural elements

    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
    .fig
    -0.07
    ammer
    -0.07
    chn
    -0.07
    ÙħÙĦØ©
    -0.07
    apgolly
    -0.06
     Uy
    -0.06
    udev
    -0.06
    tent
    -0.06
    oller
    -0.06
    _MACRO
    -0.06
    POSITIVE LOGITS
     Cherokee
    0.13
     Chief
    0.09
     Georgia
    0.09
     Removal
    0.08
     Indian
    0.08
     Creek
    0.08
    Chief
    0.08
     Sequ
    0.07
     Alabama
    0.07
    erokee
    0.07
    Activations Density 0.009%

    No Known Activations