© 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. 80424
    Prev
    Next
    INDEX
    Explanations

    political commentary and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text segments that provide contextual information, transitions between ideas, or structural elements that connect different parts of content.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    -&
    -0.07
    rex
    -0.07
     aforementioned
    -0.07
    /downloads
    -0.06
    soever
    -0.06
     anomal
    -0.06
    ÌĤ
    -0.06
     --
    -0.06
     @}
    -0.06
     ç¨
    -0.06
    POSITIVE LOGITS
     partly
    0.06
     different
    0.06
     people
    0.06
    OfWork
    0.06
    feit
    0.06
     continual
    0.06
     including
    0.06
    formace
    0.06
     automát
    0.06
     publicity
    0.06
    Activations Density 0.618%

    No Known Activations