© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 104226
    Prev
    Next
    INDEX
    Explanations

    references to organizations or entities

    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
    üz
    -0.07
    eview
    -0.07
    ÙĬÙĨا
    -0.07
    /inc
    -0.06
    :CGRect
    -0.06
    agini
    -0.06
    ัà¸Ķส
    -0.06
    Æ°á»Ŀi
    -0.06
    ollapse
    -0.06
    occo
    -0.06
    POSITIVE LOGITS
    nit
    0.07
    ul
    0.07
     Pron
    0.06
     simply
    0.06
    cho
    0.06
     pron
    0.06
    akens
    0.06
    atre
    0.06
    804
    0.06
     Pew
    0.05
    Activations Density 0.009%

    No Known Activations