© 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. 15-LLAMASCOPE-RES-131K
    11. 86007
    Prev
    Next
    INDEX
    Explanations

    terms related to proposals and considerations within a formal context

    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
     Wie
    -0.06
     hy
    -0.06
     magn
    -0.06
     Ole
    -0.06
     dob
    -0.06
     Gun
    -0.06
     ab
    -0.05
     penetr
    -0.05
     bow
    -0.05
    /or
    -0.05
    POSITIVE LOGITS
    rends
    0.08
    ÙĨدÙĤ
    0.07
    ayi
    0.07
    ackers
    0.07
    /current
    0.07
    év
    0.07
    anner
    0.07
    edList
    0.07
    uhe
    0.07
    inea
    0.07
    Activations Density 0.020%

    No Known Activations