© 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. 62957
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific methodologies and findings

    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
    isure
    -0.07
    eyse
    -0.07
    eggies
    -0.07
     Frau
    -0.06
     Flam
    -0.06
    occo
    -0.06
    =-=-=-=-=-=-=-=-
    -0.06
    PCR
    -0.06
     McGregor
    -0.06
    hir
    -0.06
    POSITIVE LOGITS
     Nature
    0.08
    npj
    0.08
    Nature
    0.07
    allet
    0.07
    layan
    0.07
     mac
    0.06
     nature
    0.06
    nature
    0.06
     programmes
    0.06
    ledon
    0.06
    Activations Density 0.056%

    No Known Activations