© 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. 84298
    Prev
    Next
    INDEX
    Explanations

    words related to web page access and viewing

    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
     Casa
    -0.06
    -
    -0.06
     cad
    -0.06
    aze
    -0.06
    adow
    -0.05
     Dawn
    -0.05
     lip
    -0.05
     unique
    -0.05
     CAS
    -0.05
    du
    -0.05
    POSITIVE LOGITS
     nghi
    0.09
    LL
    0.08
    sono
    0.08
    lie
    0.07
     addCriterion
    0.07
    ÙĤب
    0.07
    intros
    0.07
     ÄijÃŃch
    0.07
    emode
    0.07
    offline
    0.07
    Activations Density 0.001%

    No Known Activations