© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 17006
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss varying perspectives or interpretations of stories or events

    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
    ìļ´ëį°
    -0.08
    urst
    -0.08
     knull
    -0.07
    oppel
    -0.06
    æĢģ
    -0.06
    Když
    -0.06
    алеж
    -0.06
    Powered
    -0.06
    祥
    -0.06
    ullan
    -0.06
    POSITIVE LOGITS
     merely
    0.09
     obvious
    0.09
     simple
    0.08
     directly
    0.08
     simply
    0.08
     overt
    0.07
     mere
    0.07
     simplement
    0.07
     easy
    0.07
     straightforward
    0.07
    Activations Density 0.033%

    No Known Activations