© 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. 727
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications or requirements

    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
    azzi
    -0.07
    mite
    -0.07
    _guard
    -0.07
    eman
    -0.06
    statt
    -0.06
    emiz
    -0.06
    ucch
    -0.06
     ye
    -0.06
    ery
    -0.06
    Themes
    -0.06
    POSITIVE LOGITS
     special
    0.08
     designed
    0.07
    /Instruction
    0.07
     ÑģпеÑĨи
    0.07
    .removeEventListener
    0.06
    ÑĢаÑħов
    0.06
     design
    0.06
     Special
    0.06
    ìłĢ
    0.06
    special
    0.06
    Activations Density 0.013%

    No Known Activations