© 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. 94357
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to personal experiences and 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
    ÑĦоÑĢми
    -0.07
    atched
    -0.07
    amedi
    -0.07
    ho
    -0.06
    upal
    -0.06
    ÑĪев
    -0.06
    aim
    -0.06
    roke
    -0.06
    udden
    -0.06
    907
    -0.06
    POSITIVE LOGITS
     later
    0.12
     eventually
    0.10
    later
    0.10
     subsequent
    0.10
     subsequently
    0.09
     pozdÄĽji
    0.09
     Later
    0.09
     später
    0.09
    Later
    0.09
     Eventually
    0.08
    Activations Density 0.061%

    No Known Activations