© 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. 5-LLAMASCOPE-RES-131K
    11. 125503
    Prev
    Next
    INDEX
    Explanations

    elements related to characters or roles

    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
     (
    -0.07
    -0.06
     n
    -0.06
     atmos
    -0.06
    .wikipedia
    -0.06
    ,
    -0.05
     release
    -0.05
     Hutchinson
    -0.05
     as
    -0.05
     basket
    -0.05
    POSITIVE LOGITS
    LOCKS
    0.07
    arih
    0.07
    avad
    0.07
    .CopyTo
    0.07
    RIPT
    0.07
    kla
    0.07
    py
    0.07
    ë¹Ī
    0.07
    ascus
    0.07
    olders
    0.07
    Activations Density 0.000%

    No Known Activations