© 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. 94191
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating direction or transition

    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
    оÑĢони
    -0.07
    loses
    -0.07
    alytics
    -0.07
    IRON
    -0.07
    ventus
    -0.07
    ÛĮاÙĨ
    -0.07
    ele
    -0.07
    âĢ¦âĢ¦ãĢĤ
    -0.07
    YTE
    -0.07
    skirts
    -0.07
    POSITIVE LOGITS
    0.07
    ãĥ¼ãĤ¯
    0.06
    ologia
    0.06
    ãĥ¼ãĥĹ
    0.06
    nett
    0.06
     IDM
    0.06
     compact
    0.06
    reu
    0.06
    èķ
    0.05
     e
    0.05
    Activations Density 0.051%

    No Known Activations