© 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. 58201
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods related to the past

    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
    eres
    -0.07
    ÄŁan
    -0.07
     disadv
    -0.06
    jte
    -0.06
    ancock
    -0.06
    еви
    -0.06
    aby
    -0.06
    .wik
    -0.06
    ernes
    -0.06
    att
    -0.06
    POSITIVE LOGITS
     few
    0.10
    ebin
    0.08
    istrovstvÃŃ
    0.08
     several
    0.07
    /current
    0.07
     неÑģколÑĮко
    0.07
    ëħĦëıĦ
    0.07
    LinkId
    0.07
     years
    0.07
    ãģ°ãģĭãĤĬ
    0.07
    Activations Density 0.009%

    No Known Activations