© 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 EvalsExportsAPI 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. 84393
    Prev
    Next
    INDEX
    Explanations

    statements indicating uncertainty or the potential for error

    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
    нÑıв
    -0.07
     Garrison
    -0.07
    Finished
    -0.06
    ropic
    -0.06
    lope
    -0.06
    ÑĢÑĸд
    -0.06
    berger
    -0.06
     InvalidArgumentException
    -0.06
    ISR
    -0.06
    ead
    -0.06
    POSITIVE LOGITS
    ubbo
    0.07
    è¾°
    0.07
    atchet
    0.07
     عÙĨÙĩ
    0.06
    OrNil
    0.06
     nbytes
    0.06
     due
    0.06
     altogether
    0.06
    åĩºçīĪ社
    0.06
    ",__
    0.06
    Activations Density 0.006%

    No Known Activations