© 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. 69055
    Prev
    Next
    INDEX
    Explanations

    assertions and claims about personal experiences or opinions

    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
     Glad
    -0.06
    quist
    -0.06
     Laur
    -0.06
    ized
    -0.06
     Singer
    -0.05
    uid
    -0.05
     Ville
    -0.05
    aft
    -0.05
     Strand
    -0.05
    udes
    -0.05
    POSITIVE LOGITS
    chio
    0.07
    rena
    0.07
    emm
    0.07
    çļĦæĺ¯
    0.07
    à¤Ĥà¤ļ
    0.07
    berra
    0.07
     stol
    0.07
    amu
    0.07
    zell
    0.07
     definitely
    0.07
    Activations Density 0.014%

    No Known Activations