© 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. 80523
    Prev
    Next
    INDEX
    Explanations

    references to quantity or abundance in a variety of contexts

    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
     bem
    -0.07
    ally
    -0.07
    cient
    -0.07
    291
    -0.07
    ian
    -0.06
    igmatic
    -0.06
     bulk
    -0.06
    219
    -0.06
    esc
    -0.06
    221
    -0.06
    POSITIVE LOGITS
    urdu
    0.08
     ways
    0.07
    $MESS
    0.07
    íĴ
    0.07
    èİ
    0.07
    еÑĢжав
    0.07
    ÃŃch
    0.07
    eways
    0.07
     <",
    0.07
    fone
    0.07
    Activations Density 0.022%

    No Known Activations