© 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. 86282
    Prev
    Next
    INDEX
    Explanations

    key terms related to events and gatherings

    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
    å¯
    -0.07
    .nlm
    -0.06
    874
    -0.06
    uzzi
    -0.06
    878
    -0.06
    donnees
    -0.06
    quip
    -0.06
    rug
    -0.06
    aya
    -0.06
    LayoutConstraint
    -0.06
    POSITIVE LOGITS
    dsl
    0.07
    Ñģп
    0.07
    NG
    0.06
    RTL
    0.06
    /etc
    0.06
     "+"
    0.06
    _partner
    0.06
     Fasc
    0.06
     seins
    0.06
    oms
    0.06
    Activations Density 0.000%

    No Known Activations