© 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. 31629
    Prev
    Next
    INDEX
    Explanations

    comma-separated lists or series of items

    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
    Ø´ÙĪر
    -0.07
    nz
    -0.07
    AGR
    -0.06
     Ones
    -0.06
     ones
    -0.06
    xd
    -0.06
    ones
    -0.06
    others
    -0.06
    ince
    -0.06
    ilent
    -0.06
    POSITIVE LOGITS
     sebuah
    0.11
     een
    0.10
     a
    0.10
     an
    0.10
    ä¸Ģ个
    0.08
     eine
    0.08
     another
    0.08
    ä¸Ģç§į
    0.08
    æĺ¯ä¸Ģ个
    0.07
     ÎŃνα
    0.07
    Activations Density 0.040%

    No Known Activations