© 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. 127350
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and significant current events

    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
    ibraries
    -0.07
    kup
    -0.07
    :
    -0.07
    oop
    -0.07
    renom
    -0.06
     *,↵
    -0.06
    omens
    -0.06
    requency
    -0.06
    licted
    -0.06
    brids
    -0.06
    POSITIVE LOGITS
     Edition
    0.08
    $MESS
    0.07
     edition
    0.06
    .toHexString
    0.06
    .PropertyType
    0.06
    itchens
    0.06
    <decltype
    0.06
     hale
    0.06
    291
    0.06
     comp
    0.06
    Activations Density 0.059%

    No Known Activations