© 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. 58255
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and merchandise associated with Baltimore Ravens

    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
    neau
    -0.07
    nea
    -0.07
    нÑĥÑĤ
    -0.07
    kar
    -0.07
    ius
    -0.06
    âĤ¬↵
    -0.06
    ullan
    -0.06
    -Feb
    -0.06
    oteca
    -0.06
    fono
    -0.06
    POSITIVE LOGITS
     gear
    0.07
     Moy
    0.06
    reich
    0.06
     insign
    0.06
    cliffe
    0.06
    -logo
    0.06
     fans
    0.06
     revers
    0.06
     поÑĢÑıд
    0.06
     ÑģиÑĢ
    0.06
    Activations Density 0.005%

    No Known Activations