© 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. 72259
    Prev
    Next
    INDEX
    Explanations

    phrases indicating outcomes or conclusions

    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
    inz
    -0.07
     Perf
    -0.06
    ding
    -0.06
    oples
    -0.06
    ongan
    -0.06
    inan
    -0.06
    ahan
    -0.06
    udic
    -0.06
    ching
    -0.06
    iman
    -0.05
    POSITIVE LOGITS
    wards
    0.07
     bý
    0.07
    arakter
    0.07
    oty
    0.07
     toItem
    0.07
    675
    0.07
     ########.
    0.07
    yl
    0.07
    umph
    0.07
    물ìĿĦ
    0.07
    Activations Density 0.007%

    No Known Activations