© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128536
    Prev
    Next
    INDEX
    Explanations

    legal language related to jurisdiction and compliance

    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
    aminer
    -0.09
    unk
    -0.07
    uppy
    -0.07
     Indies
    -0.07
    uco
    -0.07
    ucer
    -0.06
    lesi
    -0.06
    assa
    -0.06
    Integration
    -0.06
    ork
    -0.06
    POSITIVE LOGITS
     localized
    0.07
    bol
    0.06
     residents
    0.06
    pons
    0.06
     geographic
    0.06
    iche
    0.06
     accordingly
    0.06
    mada
    0.06
    aland
    0.06
     materials
    0.06
    Activations Density 0.008%

    No Known Activations