© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58461
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "present" and its variations, indicating a focus on current events or states

    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
    panion
    -0.07
    rish
    -0.06
    lover
    -0.06
    itori
    -0.06
    enas
    -0.06
    usercontent
    -0.06
     Gu
    -0.06
    sian
    -0.06
    ses
    -0.06
    tran
    -0.06
    POSITIVE LOGITS
    -day
    0.14
    iment
    0.12
    iments
    0.10
    tlement
    0.10
    ational
    0.10
    day
    0.09
    -Day
    0.09
    IMENT
    0.08
    abelle
    0.08
    ABEL
    0.08
    Activations Density 0.011%

    No Known Activations