© 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. 2185
    Prev
    Next
    INDEX
    Explanations

    phrases that reflect change or historical context in medicine and accessibility

    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
    .hu
    -0.07
    ales
    -0.06
    ÑģÑıÑĤ
    -0.06
    ocs
    -0.06
    ampton
    -0.06
     Proof
    -0.06
    askell
    -0.06
     Sokol
    -0.06
    umbn
    -0.06
    Ỽp
    -0.06
    POSITIVE LOGITS
     nor
    0.07
     ìĿ´ëłĩê²Į
    0.07
    versions
    0.07
     necessarily
    0.06
    å¦ĤæѤ
    0.06
    radient
    0.06
     Morm
    0.06
    á»ģ
    0.06
     Borg
    0.06
    ยาà¸Ļ
    0.06
    Activations Density 0.003%

    No Known Activations