© 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. 15-LLAMASCOPE-RES-131K
    11. 90351
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to logistics and organization

    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
    .instant
    -0.07
    ntag
    -0.06
    cow
    -0.06
    á»ı
    -0.06
    hle
    -0.06
    OMEM
    -0.06
    lte
    -0.06
    INGLE
    -0.06
    .mybatisplus
    -0.06
     Bis
    -0.06
    POSITIVE LOGITS
     Kv
    0.07
    ICA
    0.07
    ud
    0.07
    urve
    0.07
    éĥ
    0.06
    wards
    0.06
    anders
    0.06
    UD
    0.06
     fuera
    0.06
     Dahl
    0.06
    Activations Density 0.027%

    No Known Activations