© 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. 86735
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and semicolons in code

    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
     compared
    -0.06
     ph
    -0.06
    esModule
    -0.06
    оÑĢÑĸв
    -0.06
    olver
    -0.06
    nce
    -0.06
    egie
    -0.06
     Nass
    -0.06
    .ut
    -0.06
    ecast
    -0.06
    POSITIVE LOGITS
    iÄį
    0.07
    .AutoScaleMode
    0.07
    rog
    0.07
    αÏģά
    0.06
    /sdk
    0.06
    zzo
    0.06
     withObject
    0.06
     Dich
    0.06
    ?url
    0.06
     NavParams
    0.06
    Activations Density 0.011%

    No Known Activations