© 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. 93986
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and control flow statements in programming contexts

    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
    anz
    -0.07
    mist
    -0.07
    UrlParser
    -0.07
    UPLE
    -0.06
    braco
    -0.06
    pector
    -0.06
    enti
    -0.06
    leDb
    -0.06
    ents
    -0.06
     parms
    -0.06
    POSITIVE LOGITS
    845
    0.07
     clam
    0.06
    arin
    0.06
    _STA
    0.06
    ville
    0.05
    arrow
    0.05
     Äiji
    0.05
    à¸ģรรม
    0.05
    505
    0.05
    ari
    0.05
    Activations Density 0.007%

    No Known Activations