© 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. 71204
    Prev
    Next
    INDEX
    Explanations

    prepositions and their uses in complex sentence structures

    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
    اسÙĩ
    -0.07
    ideo
    -0.07
    efa
    -0.07
    ucz
    -0.07
    efe
    -0.07
     Jako
    -0.06
    ilor
    -0.06
    .springboot
    -0.06
    (_,
    -0.06
    å¤
    -0.06
    POSITIVE LOGITS
    alt
    0.07
    lingen
    0.07
    quat
    0.06
    zzo
    0.06
    ALT
    0.06
    ver
    0.06
    oại
    0.06
    getSingleton
    0.06
    /autoload
    0.06
     Schmidt
    0.06
    Activations Density 0.090%

    No Known Activations