© 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. 14412
    Prev
    Next
    INDEX
    Explanations

    XML-like syntax and configuration settings

    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
    Anchor
    -0.08
    ugs
    -0.07
    arp
    -0.07
    ojis
    -0.07
    ugas
    -0.07
    iterr
    -0.07
    аÑĢд
    -0.07
    igos
    -0.07
    anchor
    -0.07
     Anchor
    -0.07
    POSITIVE LOGITS
     deck
    0.06
     McInt
    0.06
     Wolfe
    0.06
     competitive
    0.06
     Deck
    0.05
     Rey
    0.05
     Competitive
    0.05
     Bundy
    0.05
    captcha
    0.05
     depend
    0.05
    Activations Density 0.005%

    No Known Activations