© 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. 98996
    Prev
    Next
    INDEX
    Explanations

    identifiers, codes, or abbreviations related to funding or technical specifications

    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
     Chow
    -0.06
     wit
    -0.06
    574
    -0.06
    ileo
    -0.06
    aising
    -0.06
    ós
    -0.06
     Andreas
    -0.06
    ec
    -0.06
    747
    -0.06
    ys
    -0.06
    POSITIVE LOGITS
    ãģ¡ãģ¯
    0.08
    ìį¨
    0.07
    jni
    0.07
     nackte
    0.07
    .utf
    0.07
     Lor
    0.06
    ÙĦت
    0.06
     --->
    0.06
    ï¸
    0.06
     TERM
    0.06
    Activations Density 0.001%

    No Known Activations