© 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. 54054
    Prev
    Next
    INDEX
    Explanations

    instances of the word "it" and variations or context involving the concept of "it."

    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
    ROLLER
    -0.07
    forge
    -0.07
    æݧ
    -0.07
    ħ
    -0.07
    okoj
    -0.07
    kok
    -0.06
    IDDEN
    -0.06
    itches
    -0.06
    hill
    -0.06
    umed
    -0.06
    POSITIVE LOGITS
     happen
    0.09
     easy
    0.08
    ark
    0.07
     easier
    0.07
    iner
    0.07
    appen
    0.07
    anium
    0.06
    entifier
    0.06
     difficult
    0.06
     happened
    0.06
    Activations Density 0.012%

    No Known Activations