© 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 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. 84201
    Prev
    Next
    INDEX
    Explanations

    words related to specific actions or processes in a technical or procedural context

    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
    odore
    -0.07
    ogue
    -0.06
    uite
    -0.06
    ainen
    -0.06
    xing
    -0.06
    quisites
    -0.06
    841
    -0.06
     Tradable
    -0.06
    tober
    -0.06
    _simps
    -0.06
    POSITIVE LOGITS
    ernational
    0.07
    ãģĤãģ®
    0.07
    oms
    0.07
    оже
    0.07
    isode
    0.07
    moth
    0.07
    \grid
    0.07
    entimes
    0.07
    ÅĽci
    0.07
    ftware
    0.07
    Activations Density 0.259%

    No Known Activations