© 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 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. 29300
    Prev
    Next
    INDEX
    Explanations

    instances of the word "decline" and its variations, indicating a focus on decrease or deterioration

    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
    oso
    -0.08
    izable
    -0.07
    /place
    -0.07
    MOOTH
    -0.07
    feit
    -0.07
    rieve
    -0.07
    ctl
    -0.07
    cela
    -0.07
    nis
    -0.07
    illary
    -0.07
    POSITIVE LOGITS
    posables
    0.08
    afi
    0.07
    otron
    0.06
    acons
    0.06
    MBER
    0.06
    /exp
    0.06
    /de
    0.06
    à¥įद
    0.06
    .scalablytyped
    0.06
    inish
    0.06
    Activations Density 0.008%

    No Known Activations