© 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. 93317
    Prev
    Next
    INDEX
    Explanations

    phrases indicating anticipation or being the first to know 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
     vanity
    -0.06
     AS
    -0.06
     AT
    -0.06
     beyond
    -0.05
    vider
    -0.05
    /sidebar
    -0.05
    actly
    -0.05
    andas
    -0.05
    igan
    -0.05
     x
    -0.05
    POSITIVE LOGITS
    orro
    0.07
    efs
    0.07
    uggage
    0.07
    .bs
    0.07
    axon
    0.07
    ãĥ¼ãĥĵ
    0.07
    URRE
    0.07
    chia
    0.07
    alley
    0.06
     åŀ
    0.06
    Activations Density 0.001%

    No Known Activations