© 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. 27539
    Prev
    Next
    INDEX
    Explanations

    technical specifications or elements related to devices or systems

    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
    frog
    -0.07
    Ñģли
    -0.07
    sto
    -0.06
    ithub
    -0.06
    licer
    -0.06
    mir
    -0.06
     Cant
    -0.06
    inks
    -0.06
    enburg
    -0.06
    omanip
    -0.06
    POSITIVE LOGITS
    uy
    0.07
    ag
    0.06
     quart
    0.06
    ernal
    0.06
    ɵ
    0.06
    imple
    0.06
    å¾
    0.05
    åľ³
    0.05
     XmlNode
    0.05
    \Console
    0.05
    Activations Density 0.011%

    No Known Activations