© 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. 56886
    Prev
    Next
    INDEX
    Explanations

    variations of text formatting and styles

    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
    eus
    -0.08
    icer
    -0.07
    itesse
    -0.07
    vider
    -0.07
    enberg
    -0.06
    лава
    -0.06
     Kv
    -0.06
    ivamente
    -0.06
    каÑĢ
    -0.06
    chart
    -0.06
    POSITIVE LOGITS
    ized
    0.09
    ness
    0.07
    ised
    0.07
    Italic
    0.07
    NESS
    0.07
     mine
    0.07
    izing
    0.07
    ted
    0.06
    180
    0.06
    ization
    0.06
    Activations Density 0.003%

    No Known Activations