© 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. 15-LLAMASCOPE-RES-131K
    11. 27665
    Prev
    Next
    INDEX
    Explanations

    phrases that contrast or compare different subjects or ideas

    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
    аÑĢан
    -0.08
    porter
    -0.07
    rah
    -0.07
    NCY
    -0.07
     دÙĨ
    -0.07
    TEMPL
    -0.07
     eiusmod
    -0.07
    ÑģÑĤин
    -0.07
    atomy
    -0.07
    ç¤
    -0.07
    POSITIVE LOGITS
    ween
    0.07
    igator
    0.06
     than
    0.06
    ä¿Ĺ
    0.06
    934
    0.06
    /all
    0.06
    olls
    0.06
     Vide
    0.06
    ffset
    0.06
    NaN
    0.06
    Activations Density 0.002%

    No Known Activations