© 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 EvalsExportsAPI 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. 59503
    Prev
    Next
    INDEX
    Explanations

    references to historical texts and notable figures in scholarly 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
     бÑĥк
    -0.07
    ropic
    -0.07
    ISC
    -0.06
    aÄĩ
    -0.06
    /bus
    -0.06
    isan
    -0.06
    laden
    -0.06
    anyl
    -0.06
    é»ĺ
    -0.06
    ApiController
    -0.06
    POSITIVE LOGITS
     mention
    0.08
     descriptions
    0.08
    ifes
    0.08
     description
    0.07
     describing
    0.07
     gloss
    0.06
    mentions
    0.06
     loc
    0.06
    ानत
    0.06
     mentions
    0.06
    Activations Density 0.033%

    No Known Activations