© 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. 78145
    Prev
    Next
    INDEX
    Explanations

    references to legal or regulatory frameworks and protocols

    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
     ÑĢÑĥки
    -0.08
    celik
    -0.07
    otal
    -0.07
    nda
    -0.07
     ÑĢÑĥкаÑħ
    -0.07
    ženÃŃ
    -0.07
     afect
    -0.07
    _IO
    -0.07
    nez
    -0.07
    ÑĢаÑģ
    -0.07
    POSITIVE LOGITS
     instructions
    0.06
     powers
    0.06
     orders
    0.06
     agreement
    0.06
    ment
    0.06
    12
    0.06
    .EventType
    0.05
     agreements
    0.05
     Enemy
    0.05
     recommendations
    0.05
    Activations Density 0.009%

    No Known Activations