© 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. 28256
    Prev
    Next
    INDEX
    Explanations

    formatting and structural elements within a document

    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
     Worth
    -0.06
    DefaultValue
    -0.06
    ieri
    -0.06
    ault
    -0.06
    akter
    -0.06
    osal
    -0.06
     span
    -0.06
    åį
    -0.06
    jsx
    -0.06
    км
    -0.06
    POSITIVE LOGITS
     marg
    0.06
    retty
    0.06
    endor
    0.06
     cạnh
    0.06
     Patterson
    0.06
    aggio
    0.06
     Buen
    0.06
    .Automation
    0.06
    ">//
    0.06
    ead
    0.06
    Activations Density 0.005%

    No Known Activations