© 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. 70029
    Prev
    Next
    INDEX
    Explanations

    names of venues and locations associated with performances

    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
     rue
    -0.06
     god
    -0.06
     Cannes
    -0.06
     intr
    -0.06
     cul
    -0.06
     sup
    -0.06
     Arnold
    -0.05
    afa
    -0.05
    ulous
    -0.05
    宿
    -0.05
    POSITIVE LOGITS
     {{--<
    0.08
     ApplicationException
    0.08
     palindrome
    0.07
    кÑĢаÑĹ
    0.07
    Capacity
    0.07
    marshall
    0.07
    /INFO
    0.07
    capacity
    0.07
     Annex
    0.07
    nerRadius
    0.07
    Activations Density 0.021%

    No Known Activations