© 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. 61443
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Grant."

    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
    ¬
    -0.08
    WithEmail
    -0.07
     воÑĤ
    -0.07
    ë²½
    -0.07
    isplay
    -0.07
    ITY
    -0.07
    ình
    -0.07
    ernen
    -0.06
    ÅĤaw
    -0.06
    .metamodel
    -0.06
    POSITIVE LOGITS
    bach
    0.07
    ee
    0.07
    ful
    0.06
    ive
    0.06
    owy
    0.06
    ãĥģãĥ¥
    0.06
    feeding
    0.06
    ages
    0.06
    orrent
    0.06
    eworld
    0.06
    Activations Density 0.009%

    No Known Activations