© 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. 5-LLAMASCOPE-RES-131K
    11. 126022
    Prev
    Next
    INDEX
    Explanations

    references to time and occurrence

    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
    asin
    -0.07
    allas
    -0.07
    essler
    -0.06
    çĵľ
    -0.06
    idd
    -0.06
    achuset
    -0.06
    oras
    -0.06
     Hou
    -0.06
    оÑĤÑĥ
    -0.06
    ött
    -0.06
    POSITIVE LOGITS
    hti
    0.08
    oggled
    0.06
    ÅĽci
    0.06
    iteli
    0.06
    -CS
    0.06
     roster
    0.06
    922
    0.06
    clare
    0.06
    ONSE
    0.06
     Broken
    0.06
    Activations Density 0.012%

    No Known Activations