© 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. 119432
    Prev
    Next
    INDEX
    Explanations

    numeric values or references commonly associated with scientific or technical measurements

    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
    Gratis
    -0.08
    getc
    -0.07
    slick
    -0.07
    oleÄį
    -0.07
    lasses
    -0.07
    rnek
    -0.07
    Synopsis
    -0.07
    ãĥ³ãĥĹ
    -0.07
    ector
    -0.06
    ampie
    -0.06
    POSITIVE LOGITS
    itzer
    0.07
    cco
    0.07
     better
    0.07
     superior
    0.06
     Labels
    0.06
     highest
    0.06
     Better
    0.06
    rames
    0.06
     scop
    0.06
     performance
    0.06
    Activations Density 0.086%

    No Known Activations