© 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. 5-LLAMASCOPE-RES-131K
    11. 126885
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" in various contexts

    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
    ims
    -0.06
     sto
    -0.06
     fair
    -0.06
     Fair
    -0.06
    icias
    -0.06
    y
    -0.06
     wards
    -0.06
    isu
    -0.05
    i
    -0.05
    olumn
    -0.05
    POSITIVE LOGITS
    åĤĻ
    0.07
    PCP
    0.07
    veis
    0.07
    atile
    0.07
    hangi
    0.07
    INLINE
    0.07
    uggage
    0.06
    Åĺ
    0.06
    ostel
    0.06
    finity
    0.06
    Activations Density 0.015%

    No Known Activations