© 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. 127353
    Prev
    Next
    INDEX
    Explanations

    instances of the substring "ri" and variations of it in names or terms

    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
    corr
    -0.08
    st
    -0.08
    rou
    -0.07
    oS
    -0.07
    ster
    -0.07
    vis
    -0.07
    loor
    -0.07
    mat
    -0.07
    tras
    -0.07
    bast
    -0.07
    POSITIVE LOGITS
    yas
    0.11
    yaw
    0.10
    ye
    0.10
    yat
    0.10
    yar
    0.09
    ya
    0.09
    yon
    0.09
    yan
    0.09
    yum
    0.09
    ytt
    0.08
    Activations Density 0.036%

    No Known Activations