© 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. 17-LLAMASCOPE-RES-131K
    11. 77695
    Prev
    Next
    INDEX
    Explanations

    numeric values or quantities

    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
     trace
    -0.07
    iler
    -0.07
    ffi
    -0.07
     traces
    -0.07
    á»įt
    -0.07
    _asm
    -0.06
     opat
    -0.06
     inv
    -0.06
    acob
    -0.06
    ffe
    -0.06
    POSITIVE LOGITS
    367
    0.06
    atron
    0.06
    senal
    0.06
    ICA
    0.06
     pou
    0.05
     Redistributions
    0.05
    yard
    0.05
    ANNEL
    0.05
    461
    0.05
    -sdk
    0.05
    Activations Density 0.002%

    No Known Activations