© 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. 78679
    Prev
    Next
    INDEX
    Explanations

    references to publication dates and updates

    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
    kid
    -0.07
     имп
    -0.06
    SP
    -0.06
    Forge
    -0.06
    atu
    -0.06
    586
    -0.06
    Kid
    -0.06
    291
    -0.06
    atra
    -0.06
    mb
    -0.06
    POSITIVE LOGITS
    éĽĦ
    0.06
    ENSE
    0.06
    ensch
    0.06
    0.06
    baar
    0.06
     Betty
    0.06
     أبرÙĬÙĦ
    0.06
    _BOOT
    0.06
    ein
    0.06
     Toe
    0.06
    Activations Density 0.003%

    No Known Activations