© 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. 55414
    Prev
    Next
    INDEX
    Explanations

    HTML tags and script elements

    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
     Král
    -0.08
    еж
    -0.07
    esson
    -0.07
    jie
    -0.07
    isco
    -0.07
    wei
    -0.07
     Brush
    -0.07
     {}));↵
    -0.06
    ordum
    -0.06
    αιν
    -0.06
    POSITIVE LOGITS
    aint
    0.06
     resid
    0.06
    à¸ļà¸ģ
    0.06
     Hit
    0.06
    å¤ĩ
    0.05
    olio
    0.05
    aira
    0.05
     Erotic
    0.05
    iet
    0.05
    itsu
    0.05
    Activations Density 0.001%

    No Known Activations