© 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. 79671
    Prev
    Next
    INDEX
    Explanations

    specific news-related terms and phrases

    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
    pta
    -0.08
    éis
    -0.07
    isu
    -0.07
    à¥įतà¤ķ
    -0.07
    ]={↵
    -0.07
    665
    -0.07
    imuth
    -0.07
     poc
    -0.07
    arih
    -0.06
    alli
    -0.06
    POSITIVE LOGITS
     Morrow
    0.07
    strcasecmp
    0.06
     kra
    0.06
    esty
    0.05
    .camel
    0.05
     Bren
    0.05
    ilde
    0.05
     MAP
    0.05
    dden
    0.05
     "','
    0.05
    Activations Density 0.002%

    No Known Activations