© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57086
    Prev
    Next
    INDEX
    Explanations

    significant concepts related to challenges, distinctions, or critical moments in narratives

    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
    /animations
    -0.07
    .mixin
    -0.07
    atron
    -0.07
    heroes
    -0.06
    alian
    -0.06
    á»
    -0.06
     malé
    -0.06
    EMPL
    -0.06
    lero
    -0.06
    ëŀĢ
    -0.06
    POSITIVE LOGITS
     indeed
    0.09
     considering
    0.07
    838
    0.07
    IPLE
    0.07
    inde
    0.07
     Moff
    0.06
    ä¹ĭä¸Ģ
    0.06
    åĿ¡
    0.06
    imd
    0.06
    #af
    0.06
    Activations Density 0.038%

    No Known Activations