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

    Neuronpedia

    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. 85083
    Prev
    Next
    INDEX
    Explanations

    comments on organizational performance and progress

    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
    ickey
    -0.07
    .Modules
    -0.06
    edom
    -0.06
    IEW
    -0.06
    entre
    -0.06
    ORTH
    -0.06
    efe
    -0.06
    rypto
    -0.06
    102
    -0.06
    aÄŁa
    -0.05
    POSITIVE LOGITS
     itself
    0.08
    singleton
    0.07
     its
    0.07
    åıĬåħ¶
    0.07
    ernals
    0.07
    avigate
    0.07
     isize
    0.07
    nict
    0.07
    growth
    0.07
     institution
    0.07
    Activations Density 0.053%

    No Known Activations