© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126754
    Prev
    Next
    INDEX
    Explanations

    references to the Sustainable Development Goals (SDGs)

    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
     Waterloo
    -0.06
    lij
    -0.06
     via
    -0.06
    252
    -0.05
    331
    -0.05
    rote
    -0.05
     Wagner
    -0.05
    ise
    -0.05
    borne
    -0.05
    APER
    -0.05
    POSITIVE LOGITS
    tÃŃ
    0.08
    rowsable
    0.07
    zburg
    0.07
    íĨ¡
    0.07
    iedade
    0.07
    iá»ĥu
    0.07
    ÑģÑĤиÑĤ
    0.07
    iedo
    0.07
    isbury
    0.07
    족
    0.07
    Activations Density 0.003%

    No Known Activations