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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117655
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the concept of time or events that happened in particular years

    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
    iani
    -0.07
    rieg
    -0.06
    edback
    -0.06
     chain
    -0.06
     day
    -0.06
    ysqli
    -0.06
    ocoa
    -0.06
    ÙĦÙĥ
    -0.06
    ugar
    -0.06
    Chain
    -0.06
    POSITIVE LOGITS
    992
    0.08
    aha
    0.07
    unos
    0.07
    afa
    0.06
    aktiv
    0.06
    iram
    0.06
     باÙĦÙĨ
    0.06
    inging
    0.06
    ahr
    0.06
    akat
    0.06
    Activations Density 0.010%

    No Known Activations