© 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. 69132
    Prev
    Next
    INDEX
    Explanations

    references to user accounts and memberships

    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
    alta
    -0.07
    ãģĿãĤĮãģ¯
    -0.06
    iol
    -0.06
    ctr
    -0.06
     codes
    -0.06
     Carlson
    -0.06
    cept
    -0.05
    奪
    -0.05
    uy
    -0.05
    tam
    -0.05
    POSITIVE LOGITS
    AndPassword
    0.08
    å¸
    0.07
     account
    0.07
    æŀľ
    0.07
    InMillis
    0.07
    bung
    0.07
    ãĥ§
    0.07
    راد
    0.07
     rencont
    0.07
    oupon
    0.07
    Activations Density 0.007%

    No Known Activations