© 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. 121369
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant outcomes or consequences

    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
    ickerView
    -0.07
    upa
    -0.06
    uar
    -0.06
     answers
    -0.06
    eko
    -0.06
     alıp
    -0.06
    .DropDown
    -0.06
    PLL
    -0.06
    LEY
    -0.06
    WARE
    -0.06
    POSITIVE LOGITS
     backdrop
    0.15
     odds
    0.09
     against
    0.07
     backgrounds
    0.07
    Against
    0.07
     Against
    0.07
     background
    0.07
     grain
    0.07
     straw
    0.07
     detriment
    0.07
    Activations Density 0.054%

    No Known Activations