© 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. 61347
    Prev
    Next
    INDEX
    Explanations

    references to valuable or exceptional items and resources

    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
    /fw
    -0.07
    üstü
    -0.07
    eo
    -0.07
    arak
    -0.06
    /Instruction
    -0.06
    ilon
    -0.06
    LOB
    -0.06
    erin
    -0.06
    en
    -0.06
    ãģ£ãģį
    -0.06
    POSITIVE LOGITS
    èĪ¬
    0.09
     among
    0.07
     Atlas
    0.07
     ÑģÑĢеди
    0.07
    UIApplicationDelegate
    0.07
    rett
    0.06
    among
    0.06
     amongst
    0.06
    PerPage
    0.06
    blink
    0.06
    Activations Density 0.008%

    No Known Activations