© 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. 5-LLAMASCOPE-RES-131K
    11. 126825
    Prev
    Next
    INDEX
    Explanations

    instances of temporal and locational markers in narratives

    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
    irable
    -0.06
    onium
    -0.06
     dipped
    -0.06
    eid
    -0.06
    oki
    -0.06
    tains
    -0.06
    220
    -0.06
    ire
    -0.06
    onn
    -0.06
    endor
    -0.05
    POSITIVE LOGITS
    ãģ°ãģĭãĤĬ
    0.08
    رÙĩ
    0.07
    stad
    0.07
    Stage
    0.07
    .metamodel
    0.06
     ì¡
    0.06
    olini
    0.06
    _LITERAL
    0.06
    ÄĽle
    0.06
    Hum
    0.06
    Activations Density 0.028%

    No Known Activations