© 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. 57261
    Prev
    Next
    INDEX
    Explanations

    numerical values related to technical specifications and configurations

    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
    ÑĢаÐ
    -0.06
    .gradle
    -0.06
    559
    -0.06
    io
    -0.06
    era
    -0.06
    Ìģt
    -0.06
    594
    -0.06
    ERA
    -0.06
    816
    -0.06
    us
    -0.06
    POSITIVE LOGITS
    .EventQueue
    0.08
    UTERS
    0.07
    aukee
    0.07
    utow
    0.07
    acon
    0.07
    alloca
    0.07
    adesh
    0.07
    AndView
    0.07
    ukes
    0.07
     neod
    0.06
    Activations Density 0.048%

    No Known Activations