© 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. 54921
    Prev
    Next
    INDEX
    Explanations

    phrases indicating achievements or milestones

    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
     alo
    -0.07
    çĶļ
    -0.07
    ắc
    -0.07
    ega
    -0.06
    خت
    -0.06
    afone
    -0.06
    á»ĵn
    -0.06
    ublic
    -0.06
    mgr
    -0.06
     unreal
    -0.06
    POSITIVE LOGITS
     consensus
    0.07
     heights
    0.07
    504
    0.07
     levels
    0.07
     peak
    0.06
     reached
    0.06
     fork
    0.06
     peaks
    0.06
     conclusions
    0.06
     goals
    0.06
    Activations Density 0.023%

    No Known Activations