© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125366
    Prev
    Next
    INDEX
    Explanations

    references to representation and participation in events or 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
     欧
    -0.07
    olem
    -0.07
     Niet
    -0.07
    áj
    -0.07
    ANGLES
    -0.06
    ôme
    -0.06
    Ïİν
    -0.06
    tape
    -0.06
    ondon
    -0.06
    票
    -0.06
    POSITIVE LOGITS
     representation
    0.07
     Representation
    0.07
    Representation
    0.06
     country
    0.06
     Country
    0.06
     participation
    0.06
     Tu
    0.06
    aires
    0.06
    keleton
    0.06
    ÑĢÑĸб
    0.06
    Activations Density 0.000%

    No Known Activations