© 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. 124925
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Hewitt" or related variations

    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
    atical
    -0.08
    alom
    -0.06
     Wick
    -0.06
    ward
    -0.06
    ibal
    -0.06
    IONS
    -0.06
    ime
    -0.06
    zon
    -0.06
     support
    -0.06
    ayd
    -0.06
    POSITIVE LOGITS
    aukee
    0.09
    ewe
    0.09
    TON
    0.07
    ãĤĽ
    0.07
    tons
    0.07
    itt
    0.07
    czy
    0.07
    ew
    0.07
    gross
    0.07
     Gross
    0.07
    Activations Density 0.025%

    No Known Activations