© 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. 17-LLAMASCOPE-RES-131K
    6. 128371
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax or structures

    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
    itoris
    -0.08
    uchar
    -0.08
    ocommerce
    -0.08
    unsch
    -0.07
    imen
    -0.07
    morgan
    -0.07
    Ordinal
    -0.07
    swire
    -0.07
    .Alpha
    -0.07
    icy
    -0.06
    POSITIVE LOGITS
    asin
    0.06
     JAXBElement
    0.05
     Klein
    0.05
    AndView
    0.05
     NAS
    0.05
     assisted
    0.05
    Ruby
    0.05
     new
    0.05
     general
    0.05
     PED
    0.05
    Activations Density 0.001%

    No Known Activations