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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78101
    Prev
    Next
    INDEX
    Explanations

    instances of locations and times within a narrative context

    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
    utzer
    -0.07
    ottes
    -0.07
    arez
    -0.07
    aoke
    -0.06
    _IOC
    -0.06
    ocard
    -0.06
    اÙĪÙĬØ©
    -0.06
    utherland
    -0.06
    apur
    -0.06
    _APB
    -0.06
    POSITIVE LOGITS
     Presence
    0.07
     presence
    0.07
    swer
    0.07
    parallel
    0.06
     parallel
    0.06
     downtown
    0.06
    permalink
    0.06
    plen
    0.06
    INO
    0.06
     Ho
    0.06
    Activations Density 0.018%

    No Known Activations