© 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 EvalsExportsinterp-engineNEWAPI 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. 41944
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and hypothetical statements

    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
    ymes
    -0.07
     olursa
    -0.07
    gren
    -0.07
    als
    -0.07
    ulture
    -0.06
    972
    -0.06
    .li
    -0.06
    Ïįν
    -0.06
    eken
    -0.06
     increasingly
    -0.06
    POSITIVE LOGITS
     probably
    0.07
    probably
    0.07
     instead
    0.07
    .ArgumentParser
    0.07
    bast
    0.07
     perhaps
    0.06
    PEAR
    0.06
    lfw
    0.06
    enia
    0.06
    pard
    0.06
    Activations Density 0.031%

    No Known Activations