© 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. 9-LLAMASCOPE-RES-131K
    11. 99003
    Prev
    Next
    INDEX
    Explanations

    references to AJAX in scripts or links

    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
    opal
    -0.07
    431
    -0.07
    urm
    -0.06
    CU
    -0.06
     SU
    -0.06
    ges
    -0.06
     convenience
    -0.05
     council
    -0.05
    GGLE
    -0.05
    anten
    -0.05
    POSITIVE LOGITS
    дÑĢом
    0.08
    ONS
    0.08
    $MESS
    0.08
    ippo
    0.07
    .heroku
    0.07
     اÙĦØŃÙĬ
    0.07
    #
    0.07
    .reply
    0.07
    alyzed
    0.07
    sı
    0.07
    Activations Density 0.000%

    No Known Activations