© 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. 91666
    Prev
    Next
    INDEX
    Explanations

    references to technical topics and details

    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
    otech
    -0.08
    еÑģÑı
    -0.08
    kinson
    -0.06
    avr
    -0.06
    bad
    -0.06
    á»Ļng
    -0.06
    eg
    -0.06
    avel
    -0.06
    empl
    -0.06
    lass
    -0.06
    POSITIVE LOGITS
    ities
    0.13
    ity
    0.10
    /math
    0.08
    ité
    0.08
    icken
    0.07
    ität
    0.07
    ization
    0.07
    ITY
    0.07
    ickers
    0.07
    /engine
    0.07
    Activations Density 0.010%

    No Known Activations