© 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. 127725
    Prev
    Next
    INDEX
    Explanations

    prepositions and directional phrases that indicate relationships and movement

    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
    /Gate
    -0.10
     огÑĢа
    -0.10
    blr
    -0.10
     pornos
    -0.10
     totiž
    -0.10
    iddet
    -0.10
    .scalablytyped
    -0.10
    Å¡ker
    -0.10
    /Area
    -0.10
    [".
    -0.10
    POSITIVE LOGITS
    0.09
     both
    0.08
    ↵
    0.08
     the
    0.08
     .
    0.07
     c
    0.07
    .
    0.07
     a
    0.07
    .↵
    0.07
     multiple
    0.07
    Activations Density 0.131%

    No Known Activations