© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 125708
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'Montgomery.'

    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
    ovice
    -0.07
    idl
    -0.07
    erne
    -0.07
     GOODMAN
    -0.07
    ERGE
    -0.07
    tdown
    -0.07
    itage
    -0.07
    STREAM
    -0.07
    ccess
    -0.07
    bucket
    -0.07
    POSITIVE LOGITS
    shire
    0.11
    agne
    0.09
    lass
    0.07
    ville
    0.07
    s
    0.07
    eshire
    0.06
    agna
    0.06
    ains
    0.06
    -Clause
    0.06
    gomery
    0.06
    Activations Density 0.002%

    No Known Activations