© 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. 62949
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    esson
    -0.07
    ÑĢеб
    -0.07
    sic
    -0.07
    ç¨ĭ
    -0.07
    овеÑĢ
    -0.06
    μαÏĦο
    -0.06
    aris
    -0.06
    IOD
    -0.06
    _rq
    -0.06
    аÑĢÑħ
    -0.06
    POSITIVE LOGITS
     indeed
    0.13
     certainly
    0.10
     maybe
    0.09
    inde
    0.08
     Indeed
    0.08
     lord
    0.07
    maybe
    0.07
    ï¼Įä½Ĩ
    0.07
    Indeed
    0.07
    may
    0.07
    Activations Density 0.037%

    No Known Activations