© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90629
    Prev
    Next
    INDEX
    Explanations

    questions starting with "How."

    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
    chw
    -0.07
    encer
    -0.07
    221
    -0.06
    -ли
    -0.06
    ayah
    -0.06
    owered
    -0.06
    aeda
    -0.06
    kün
    -0.06
    allon
    -0.06
    thritis
    -0.06
    POSITIVE LOGITS
    asm
    0.07
    ihan
    0.06
    astro
    0.06
    REA
    0.06
    ienia
    0.06
    design
    0.05
    796
    0.05
     Bard
    0.05
     Liver
    0.05
    isms
    0.05
    Activations Density 0.000%

    No Known Activations