© 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. 28650
    Prev
    Next
    INDEX
    Explanations

    temporal markers and sequences in 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
     ê°Ģìłķ
    -0.06
    xes
    -0.06
    rollo
    -0.06
    oss
    -0.06
     ÑĪÑĤÑĥ
    -0.06
    endon
    -0.06
    Collision
    -0.06
     Rem
    -0.06
    аÑĢод
    -0.06
     плен
    -0.06
    POSITIVE LOGITS
    ulumi
    0.06
    rud
    0.06
     moments
    0.06
    739
    0.06
     Moments
    0.06
     ticket
    0.06
     konkrét
    0.06
    ehler
    0.06
    izar
    0.06
    iconductor
    0.06
    Activations Density 0.002%

    No Known Activations