© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 41273
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and error handling terms

    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
     belts
    -0.07
    sert
    -0.06
    esh
    -0.06
    estr
    -0.06
    esian
    -0.06
    ominator
    -0.06
    estic
    -0.06
    ẳng
    -0.06
    sut
    -0.06
    emark
    -0.06
    POSITIVE LOGITS
    adians
    0.07
     Malone
    0.07
    linky
    0.06
    portun
    0.06
    unday
    0.06
    ovol
    0.06
    343
    0.06
     Payload
    0.06
     unfolded
    0.06
     Franti
    0.06
    Activations Density 0.001%

    No Known Activations