© 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 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. 88424
    Prev
    Next
    INDEX
    Explanations

    repeated symbols or patterns in a string

    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
     thunk
    -0.06
    enc
    -0.06
    iris
    -0.06
     exterior
    -0.06
     th
    -0.06
    eno
    -0.06
    erial
    -0.05
     Stick
    -0.05
     mutil
    -0.05
     Haven
    -0.05
    POSITIVE LOGITS
    ISCO
    0.07
    ushman
    0.07
    shr
    0.07
     preferredStyle
    0.07
    741
    0.07
     Burnett
    0.07
    otch
    0.07
    YK
    0.07
    098
    0.07
    .Scene
    0.07
    Activations Density 0.000%

    No Known Activations