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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 95341
    Prev
    Next
    INDEX
    Explanations

    inquiries and questions about actions and consequences

    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
    kt
    -0.07
    å¡Ķ
    -0.07
    å¾Ĺ
    -0.06
    .stamp
    -0.06
     dise
    -0.06
    apur
    -0.06
    DS
    -0.06
    ãģ»ãģ©
    -0.06
     ds
    -0.06
     Kob
    -0.06
    POSITIVE LOGITS
     happen
    0.10
     happening
    0.10
     happens
    0.10
     happened
    0.08
     Happ
    0.08
     scenario
    0.08
     aconte
    0.08
    _scenario
    0.07
     happ
    0.07
    scenario
    0.07
    Activations Density 0.025%

    No Known Activations