© 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. 15-LLAMASCOPE-RES-131K
    6. 90700
    Prev
    Next
    INDEX
    Explanations

    references to mathematical operations and programming syntax

    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
    toi
    -0.06
    quisition
    -0.06
    trand
    -0.06
    isci
    -0.06
    aber
    -0.06
    ra
    -0.06
    @qq
    -0.06
    olen
    -0.06
    raw
    -0.06
    egas
    -0.06
    POSITIVE LOGITS
     previous
    0.22
     existing
    0.20
     previously
    0.20
     already
    0.19
     Previous
    0.18
    existing
    0.17
    previous
    0.17
     Previously
    0.17
    Previous
    0.17
     Already
    0.17
    Activations Density 0.260%

    No Known Activations