© 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. 15988
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate exceptions or comparative advantages

    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
     Leer
    -0.06
     Butler
    -0.06
     Mud
    -0.06
    ":[{↵
    -0.06
     Trev
    -0.06
    allet
    -0.06
     Kai
    -0.06
    ostel
    -0.05
     Explanation
    -0.05
    éĴĪ
    -0.05
    POSITIVE LOGITS
     physical
    0.08
    physical
    0.08
    íģ¬ê¸°
    0.07
    Ð¤ÐĽ
    0.07
    Physical
    0.07
    891
    0.07
    ELS
    0.07
    821
    0.07
     Physical
    0.07
    UCH
    0.07
    Activations Density 0.028%

    No Known Activations