© 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. 26833
    Prev
    Next
    INDEX
    Explanations

    the word "specific" and its variations in different 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
    ร
    -0.08
    اÙĨÙĩ
    -0.07
    our
    -0.07
    ony
    -0.07
    ryn
    -0.07
    mand
    -0.06
    work
    -0.06
    èm
    -0.06
    ifr
    -0.06
    up
    -0.06
    POSITIVE LOGITS
    ities
    0.12
    ally
    0.12
    ity
    0.12
    -purpose
    0.11
    ALLY
    0.11
    ially
    0.11
    ITY
    0.08
    -minded
    0.08
    /general
    0.08
    itarian
    0.08
    Activations Density 0.020%

    No Known Activations