© 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. 79120
    Prev
    Next
    INDEX
    Explanations

    code related to geometry and vector mathematics

    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
    osy
    -0.08
    erif
    -0.08
    ieux
    -0.08
    gio
    -0.07
    poz
    -0.07
    .circular
    -0.07
    rikes
    -0.07
    abase
    -0.07
    auge
    -0.07
     Jug
    -0.07
    POSITIVE LOGITS
     Norm
    0.07
     damp
    0.07
     subs
    0.06
     norm
    0.06
     Dirt
    0.06
    Norm
    0.06
     cof
    0.06
    åĤ¨
    0.06
    Kin
    0.05
    ,copy
    0.05
    Activations Density 0.120%

    No Known Activations