© 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. 40998
    Prev
    Next
    INDEX
    Explanations

    sequences of text involving the word "so" and variations or phonemes associated with it

    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
    ibilit
    -0.07
    ÙĪز
    -0.07
    urally
    -0.06
    nova
    -0.06
    fur
    -0.06
    าà¸ķร
    -0.06
    elmet
    -0.06
    ored
    -0.06
    جÙĦ
    -0.06
    zug
    -0.06
    POSITIVE LOGITS
    ffset
    0.09
    isy
    0.07
    onor
    0.07
    etest
    0.07
    thus
    0.07
    kins
    0.07
    l
    0.07
    ter
    0.06
    865
    0.06
    iske
    0.06
    Activations Density 0.017%

    No Known Activations