© 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. 5977
    Prev
    Next
    INDEX
    Explanations

    phrases indicating sudden increases in numbers or occurrences, often related to health or societal issues

    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
    ERÄ°
    -0.07
    noinspection
    -0.07
    nels
    -0.07
    ising
    -0.06
     tol
    -0.06
     crank
    -0.06
    -wage
    -0.06
    place
    -0.06
    -world
    -0.06
    ERV
    -0.06
    POSITIVE LOGITS
    oload
    0.07
    aroo
    0.07
    ivet
    0.07
    omnia
    0.07
     popularity
    0.07
    rish
    0.07
    alars
    0.06
    ваÑĤ
    0.06
     surge
    0.06
    Drv
    0.06
    Activations Density 0.010%

    No Known Activations