© 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. 89733
    Prev
    Next
    INDEX
    Explanations

    instances of the conjunction "and" in various 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
    á»ħ
    -0.07
    .ActionListener
    -0.07
    boom
    -0.07
    myModal
    -0.07
     rencont
    -0.07
    ngr
    -0.07
    onical
    -0.07
    oenix
    -0.07
    ieri
    -0.07
    cased
    -0.07
    POSITIVE LOGITS
     dig
    0.08
    rogen
    0.07
     understanding
    0.07
    705
    0.07
    mit
    0.07
    aden
    0.06
     flex
    0.06
    838
    0.06
     Dig
    0.06
     trop
    0.06
    Activations Density 0.026%

    No Known Activations