© 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. 86434
    Prev
    Next
    INDEX
    Explanations

    concepts related to challenges in practical applications or problem-solving

    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
    adium
    -0.07
    çĤ
    -0.06
    Alchemy
    -0.06
    reh
    -0.06
     weer
    -0.06
    Enumerator
    -0.06
     vole
    -0.06
    MetaData
    -0.06
    OMEM
    -0.06
    ombat
    -0.06
    POSITIVE LOGITS
    enstein
    0.08
    iated
    0.07
    erdale
    0.07
    enou
    0.07
     FileAccess
    0.07
    浩
    0.07
    ุà¸Ĺ
    0.07
     Worse
    0.06
    UrlParser
    0.06
    ingleton
    0.06
    Activations Density 0.013%

    No Known Activations