© 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. 15-LLAMASCOPE-RES-131K
    11. 90200
    Prev
    Next
    INDEX
    Explanations

    economic impacts and assessments related to trade agreements and models

    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
    atte
    -0.06
    eer
    -0.06
    lobals
    -0.06
    ÌĨ
    -0.06
    anik
    -0.06
     Nev
    -0.06
    pty
    -0.06
    ritt
    -0.06
    _mC
    -0.06
    Ùħبر
    -0.06
    POSITIVE LOGITS
     interventions
    0.08
    Ñħи
    0.07
     proposed
    0.07
     decisions
    0.07
     proposals
    0.07
     actions
    0.07
    ute
    0.07
    icular
    0.07
     various
    0.07
     intervention
    0.07
    Activations Density 0.050%

    No Known Activations