© 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. 61958
    Prev
    Next
    INDEX
    Explanations

    references to creating, managing, or using lists and tools for 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
    ban
    -0.07
    姫
    -0.06
    åĺ
    -0.06
     Ezra
    -0.06
    uego
    -0.06
    ảng
    -0.06
    oui
    -0.06
    burgh
    -0.06
    isoft
    -0.06
    olina
    -0.06
    POSITIVE LOGITS
    grav
    0.07
     Bender
    0.06
     commercially
    0.06
    erland
    0.06
    132
    0.06
    ĸī
    0.06
    Mage
    0.06
    hear
    0.06
     Intercept
    0.06
     pend
    0.06
    Activations Density 0.076%

    No Known Activations