© 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. 116547
    Prev
    Next
    INDEX
    Explanations

    phrases containing parentheses or referencing historical contexts

    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
    ifax
    -0.06
    à¸ļาà¸Ĺ
    -0.06
    nap
    -0.06
    ãĥĥãĥĦ
    -0.06
    ίδα
    -0.06
     ph
    -0.05
    anco
    -0.05
    olini
    -0.05
     кÑĥп
    -0.05
    ropri
    -0.05
    POSITIVE LOGITS
     now
    0.17
    now
    0.15
    -now
    0.14
     later
    0.13
    later
    0.13
    (now
    0.12
    çİ°åľ¨
    0.12
     eventual
    0.12
     Now
    0.12
     ahora
    0.12
    Activations Density 0.016%

    No Known Activations