© 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. 61460
    Prev
    Next
    INDEX
    Explanations

    phrases indicating references to licenses or legal disclaimers

    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
    iddi
    -0.08
    nonnull
    -0.07
    apest
    -0.07
    forman
    -0.07
    adir
    -0.07
    mgr
    -0.07
    chnitt
    -0.07
    imson
    -0.07
    oni
    -0.07
    kee
    -0.06
    POSITIVE LOGITS
    opy
    0.06
     Rib
    0.06
    uze
    0.06
    876
    0.06
     '+'
    0.06
    éĺ
    0.06
     infra
    0.05
     Lind
    0.05
    aunch
    0.05
     bahis
    0.05
    Activations Density 0.003%

    No Known Activations