© 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. 108892
    Prev
    Next
    INDEX
    Explanations

    snippets of code related to control flow and output operations

    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
     whom
    -0.07
     simply
    -0.06
     háºŃu
    -0.06
    инкÑĥ
    -0.06
    BOOLE
    -0.06
    @js
    -0.06
    akis
    -0.06
    Ñıк
    -0.06
    èĨľ
    -0.06
     dispatch
    -0.06
    POSITIVE LOGITS
     Similarly
    0.11
     Likewise
    0.11
    Similarly
    0.11
     similarly
    0.10
    Lik
    0.09
     Dit
    0.09
     likewise
    0.08
     Secondly
    0.07
    dit
    0.07
     dit
    0.07
    Activations Density 0.073%

    No Known Activations