© 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. 81264
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory changes

    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
     decomposition
    -0.07
     Mandal
    -0.07
     kut
    -0.06
    åĬłå·¥
    -0.06
    ç¸
    -0.06
     mandated
    -0.06
    ceeded
    -0.06
    oop
    -0.06
    oom
    -0.06
     Decom
    -0.06
    POSITIVE LOGITS
     rules
    0.12
    rules
    0.10
     Rules
    0.09
     definition
    0.08
     handling
    0.07
    Rules
    0.07
     interpretation
    0.07
     definitions
    0.07
    _rules
    0.07
     laws
    0.07
    Activations Density 0.031%

    No Known Activations