© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91871
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement or transitions into different states or environments

    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
    ilio
    -0.07
    entai
    -0.06
    oba
    -0.06
     éĩ
    -0.06
    lá
    -0.06
    pio
    -0.06
    anton
    -0.06
     Malik
    -0.06
    оба
    -0.06
     Ghost
    -0.06
    POSITIVE LOGITS
     everyday
    0.07
    casecmp
    0.07
    íĭĢ
    0.07
    ioctl
    0.06
    ImageContext
    0.06
    ropa
    0.06
    IDGET
    0.06
    ulle
    0.06
    ingleton
    0.06
    ustry
    0.06
    Activations Density 0.020%

    No Known Activations