© 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. 96189
    Prev
    Next
    INDEX
    Explanations

    information related to guidelines and regulations

    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
    é§ħå¾ĴæŃ©
    -0.11
    #
    -0.10
    @nate
    -0.10
    ryfall
    -0.09
    _mD
    -0.09
    _mC
    -0.09
    //{{
    -0.09
    ãĥ»ãĥ»ãĥ»↵↵
    -0.08
    using
    -0.08
    ynch
    -0.08
    POSITIVE LOGITS
     as
    0.07
    0.06
     pave
    0.06
     l
    0.06
     lie
    0.06
     which
    0.06
    ä¸ĢäºĽ
    0.06
     cum
    0.06
     equipments
    0.06
    asz
    0.06
    Activations Density 0.704%

    No Known Activations