© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 95185
    Prev
    Next
    INDEX
    Explanations

    structured code syntax elements

    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
    owie
    -0.06
    kbd
    -0.06
    imli
    -0.06
    arda
    -0.06
    SSID
    -0.06
     queryInterface
    -0.06
    ento
    -0.06
     boh
    -0.06
    BD
    -0.06
    SEO
    -0.06
    POSITIVE LOGITS
     break
    0.09
    @endif
    0.07
     But
    0.07
    lok
    0.07
    lesen
    0.07
    ':''
    0.07
    fox
    0.07
    vig
    0.06
    icas
    0.06
    igy
    0.06
    Activations Density 0.096%

    No Known Activations