© 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. 15-LLAMASCOPE-RES-131K
    11. 86131
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional words that indicate connections or shifts in ideas

    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
    ãĥĨãĥ«
    -0.09
    rish
    -0.07
    ιά
    -0.07
    Routine
    -0.07
    _Il
    -0.07
    etin
    -0.07
    UDO
    -0.07
     khÃŃ
    -0.07
    ABCDE
    -0.07
    ÏĢÏĮ
    -0.07
    POSITIVE LOGITS
    ason
    0.07
    ASON
    0.06
     He
    0.06
     then
    0.06
     thus
    0.06
    972
    0.06
    idi
    0.05
     Hoy
    0.05
    azu
    0.05
     he
    0.05
    Activations Density 0.090%

    No Known Activations