© 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. 105573
    Prev
    Next
    INDEX
    Explanations

    repeated and significant mentions of '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
    937
    -0.06
    est
    -0.06
    reira
    -0.06
    missive
    -0.06
    amy
    -0.06
     Integrity
    -0.06
     '
    -0.05
     Myst
    -0.05
     Samuel
    -0.05
    ilda
    -0.05
    POSITIVE LOGITS
    _processors
    0.08
    oret
    0.08
    ftime
    0.08
    ITCH
    0.07
    vault
    0.07
    _documento
    0.07
    ujet
    0.07
    irket
    0.07
    aks
    0.07
    èį
    0.07
    Activations Density 0.006%

    No Known Activations