© 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. 5913
    Prev
    Next
    INDEX
    Explanations

    HTML or JavaScript syntax elements

    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
    ÑĥлÑĮ
    -0.06
    æŁ»
    -0.06
     Sing
    -0.06
    frauen
    -0.06
    asher
    -0.06
    707
    -0.06
    $LANG
    -0.06
     Coy
    -0.06
    ulkan
    -0.06
    ¯¯¯¯
    -0.06
    POSITIVE LOGITS
    ÙĦاÙĦ
    0.07
    <!--<
    0.07
    (/*
    0.07
    //$
    0.06
     Quang
    0.06
     tup
    0.06
     ob
    0.06
    assi
    0.06
    ollo
    0.06
    /*
    0.06
    Activations Density 0.025%

    No Known Activations