© 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. 77320
    Prev
    Next
    INDEX
    Explanations

    URLs or references to social media statuses

    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
    é½
    -0.07
    udge
    -0.06
    ÑĥлÑİ
    -0.06
    earch
    -0.06
    ova
    -0.06
    ega
    -0.06
    ogl
    -0.06
     revers
    -0.06
    é
    -0.06
    ÑĤап
    -0.06
    POSITIVE LOGITS
    efa
    0.09
     noreferrer
    0.08
    abyrinth
    0.07
    ighth
    0.07
    anitize
    0.06
     Hayden
    0.06
    ÃŃž
    0.06
     Seamless
    0.06
    lette
    0.06
    omin
    0.06
    Activations Density 0.000%

    No Known Activations