© 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. 63297
    Prev
    Next
    INDEX
    Explanations

    possessive forms of the word "is" or its contractions

    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
    lst
    -0.07
     underwent
    -0.06
    ves
    -0.06
    صد
    -0.06
     podrob
    -0.06
    acus
    -0.06
    avanaugh
    -0.06
    zte
    -0.06
    atics
    -0.06
     undergoing
    -0.06
    POSITIVE LOGITS
     been
    0.19
    been
    0.17
     Been
    0.16
    Been
    0.15
     BEEN
    0.14
     become
    0.12
     sido
    0.10
     got
    0.10
     été
    0.09
     come
    0.08
    Activations Density 0.046%

    No Known Activations