© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1164
    Prev
    Next
    INDEX
    Explanations

    references to locations and movements

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    opher
    -0.09
     wÅĤa
    -0.07
    á»ı
    -0.07
    жи
    -0.07
    /memory
    -0.07
    jie
    -0.07
    fred
    -0.07
    ì¹ĺ를
    -0.07
     кла
    -0.07
    ugu
    -0.07
    POSITIVE LOGITS
     elsewhere
    0.09
     Else
    0.06
    072
    0.06
    Else
    0.06
    697
    0.06
    kü
    0.06
    043
    0.06
    ÑĢав
    0.06
    459
    0.06
    878
    0.06
    Activations Density 0.003%

    No Known Activations