© 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. 69710
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a relative comparison or degree of something

    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
    essen
    -0.06
    .gov
    -0.06
    plen
    -0.06
    188
    -0.06
    oshi
    -0.06
     various
    -0.06
    552
    -0.06
    arken
    -0.06
    illet
    -0.06
    fox
    -0.05
    POSITIVE LOGITS
     recently
    0.08
     speaking
    0.08
    eyh
    0.07
    -sized
    0.07
    recent
    0.07
    -priced
    0.07
    yl
    0.07
    657
    0.07
    layan
    0.07
    -ÑĤаки
    0.07
    Activations Density 0.005%

    No Known Activations