© 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. 40985
    Prev
    Next
    INDEX
    Explanations

    passive voice constructions and conditional phrases

    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
    elop
    -0.06
    /stretch
    -0.06
    aire
    -0.06
    .usage
    -0.06
    olit
    -0.06
     mechanical
    -0.06
     KEY
    -0.06
    aeda
    -0.06
     promin
    -0.06
    tec
    -0.06
    POSITIVE LOGITS
    etz
    0.07
    able
    0.07
    unable
    0.07
     able
    0.07
     designed
    0.06
    mlink
    0.06
     constructed
    0.06
    etus
    0.06
     burden
    0.06
    _Construct
    0.06
    Activations Density 0.107%

    No Known Activations