© 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. 3145
    Prev
    Next
    INDEX
    Explanations

    instances of the word "present" and its variations

    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
    ola
    -0.06
    spar
    -0.06
     пÑĢивед
    -0.06
    lder
    -0.06
    essian
    -0.05
    emb
    -0.05
    aised
    -0.05
    /k
    -0.05
    lex
    -0.05
    age
    -0.05
    POSITIVE LOGITS
     Ñģобой
    0.13
     ÑģобоÑİ
    0.09
    encing
    0.07
    812
    0.07
    iments
    0.07
    chied
    0.07
    ertino
    0.07
    wahl
    0.07
    931
    0.07
    axon
    0.07
    Activations Density 0.019%

    No Known Activations