© 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. 92153
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" in various contexts

    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
    Ñĩини
    -0.07
    ersen
    -0.06
    Synopsis
    -0.06
    ADVERTISEMENT
    -0.06
    ader
    -0.06
    .Rad
    -0.05
    .eval
    -0.05
    ¶Į
    -0.05
    hawks
    -0.05
     Hunt
    -0.05
    POSITIVE LOGITS
     same
    0.08
     entire
    0.08
    same
    0.07
    .googleapis
    0.07
     SAME
    0.07
     же
    0.07
    mil
    0.07
    .infinity
    0.07
     _
    0.06
    082
    0.06
    Activations Density 0.049%

    No Known Activations