© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62265
    Prev
    Next
    INDEX
    Explanations

    punctuation, domain names, and price mentions

    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
    áš
    -0.08
    StackSize
    -0.08
    celik
    -0.08
    omor
    -0.07
    imento
    -0.07
    dia
    -0.07
    аÑĢÑĩ
    -0.07
    ï¼ģï¼ģ↵↵
    -0.07
    xec
    -0.07
    ẻ
    -0.07
    POSITIVE LOGITS
     domain
    0.09
     domains
    0.09
     Domain
    0.07
    Domains
    0.07
     gag
    0.07
    -domain
    0.07
    domain
    0.07
     package
    0.06
    Domain
    0.06
    domains
    0.06
    Activations Density 0.000%

    No Known Activations