© 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. 16858
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching or seeking something

    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
    огод
    -0.07
    evt
    -0.07
    PED
    -0.06
    uli
    -0.06
    ION
    -0.06
     Strait
    -0.06
    atis
    -0.06
    æµľ
    -0.06
    NR
    -0.06
    __$
    -0.06
    POSITIVE LOGITS
    .datab
    0.07
    à¸Ľà¸¥
    0.06
    ohana
    0.06
    nesc
    0.06
    antu
    0.06
    anto
    0.06
    CriticalSection
    0.06
    øre
    0.06
    adele
    0.06
    lobals
    0.06
    Activations Density 0.001%

    No Known Activations