© 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. 121198
    Prev
    Next
    INDEX
    Explanations

    important nouns that signify key subjects or themes in various contexts

    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
    idores
    -0.08
    ihar
    -0.07
    cha
    -0.07
    lington
    -0.07
    idor
    -0.07
    agua
    -0.07
    mey
    -0.07
    å®ľ
    -0.07
    /Common
    -0.07
    isters
    -0.07
    POSITIVE LOGITS
     most
    0.07
    aylor
    0.06
    kate
    0.06
     that
    0.06
     MOST
    0.06
    оÑĢд
    0.06
    matic
    0.05
     GO
    0.05
     envy
    0.05
    ãĥ³ãĤ¿
    0.05
    Activations Density 0.026%

    No Known Activations