© 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. 75776
    Prev
    Next
    INDEX
    Explanations

    numerical values related to property features

    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
    ürk
    -0.07
    otal
    -0.07
    kám
    -0.06
    führ
    -0.06
    ÙĬØ·
    -0.06
    .deb
    -0.06
    rame
    -0.06
    olini
    -0.06
    STRUCTIONS
    -0.06
    ledon
    -0.06
    POSITIVE LOGITS
     Pun
    0.07
    ãĥ¼ãĥ©
    0.06
     Equ
    0.06
     living
    0.06
     Germ
    0.05
     bathroom
    0.05
    )data
    0.05
     Captain
    0.05
    >(*
    0.05
     Tout
    0.05
    Activations Density 0.003%

    No Known Activations