© 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. 14435
    Prev
    Next
    INDEX
    Explanations

    terms related to increases in quantity or magnitude

    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
    owell
    -0.07
    equality
    -0.07
    388
    -0.06
    ÏĮÏģ
    -0.06
    esin
    -0.06
    ÅĻez
    -0.06
    xab
    -0.06
    295
    -0.06
    eden
    -0.06
    978
    -0.06
    POSITIVE LOGITS
    adir
    0.08
    ongan
    0.07
    /qu
    0.07
    UnitTest
    0.07
    cient
    0.06
    igit
    0.06
    -digit
    0.06
    lix
    0.06
    ided
    0.06
    raz
    0.06
    Activations Density 0.010%

    No Known Activations