© 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. 17-LLAMASCOPE-RES-131K
    11. 118135
    Prev
    Next
    INDEX
    Explanations

    information related to event details and administrative content

    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
    uzzi
    -0.08
    loff
    -0.06
    ombres
    -0.06
     Schul
    -0.06
    mé
    -0.06
    anza
    -0.06
     metros
    -0.06
     vur
    -0.06
     Sheep
    -0.06
    umm
    -0.06
    POSITIVE LOGITS
     Mate
    0.07
    е
    0.07
    andbox
    0.07
    hic
    0.07
     Dude
    0.07
    imir
    0.06
     е
    0.06
    Ñģ
    0.06
     Babe
    0.06
    tlement
    0.06
    Activations Density 0.002%

    No Known Activations