© 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. 94535
    Prev
    Next
    INDEX
    Explanations

    expressions of opinion and conjecture

    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
    lients
    -0.07
    izzo
    -0.07
    mund
    -0.07
    .Debugf
    -0.06
    ypress
    -0.06
    alis
    -0.06
    æ´¥
    -0.06
    rokes
    -0.06
    ugo
    -0.06
    енз
    -0.06
    POSITIVE LOGITS
    iversit
    0.06
    MING
    0.06
    EntityType
    0.06
    omm
    0.06
    ered
    0.06
    etter
    0.06
    ably
    0.06
    opal
    0.06
    odium
    0.05
    .cc
    0.05
    Activations Density 0.012%

    No Known Activations