© 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. 17-LLAMASCOPE-RES-131K
    11. 71513
    Prev
    Next
    INDEX
    Explanations

    dates and their associated 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
    otron
    -0.08
    ÑĪка
    -0.08
    å±Ĭ
    -0.08
    ~-
    -0.07
    Iso
    -0.07
    igmoid
    -0.07
     воÑĤ
    -0.07
    .dom
    -0.07
    ether
    -0.07
    znám
    -0.07
    POSITIVE LOGITS
    IPS
    0.06
    obe
    0.05
    apper
    0.05
     Wishlist
    0.05
    adden
    0.05
    /rs
    0.05
     spared
    0.05
    uge
    0.05
    _medium
    0.05
    uitka
    0.05
    Activations Density 0.020%

    No Known Activations