© 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. 75549
    Prev
    Next
    INDEX
    Explanations

    instances of the word "acknowledge" and its derivatives

    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
    resh
    -0.07
    MOTE
    -0.07
    sko
    -0.07
     nackte
    -0.07
    ombie
    -0.07
    /if
    -0.07
    ëįĺ
    -0.07
    ago
    -0.07
    ارک
    -0.07
    Ñįн
    -0.07
    POSITIVE LOGITS
    nowled
    0.09
    ably
    0.09
     receipt
    0.08
     existence
    0.08
     defeat
    0.08
     rằng
    0.08
     presence
    0.07
    nowledge
    0.07
    receipt
    0.07
     past
    0.07
    Activations Density 0.008%

    No Known Activations