© 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. 117102
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intentions or instructions related to actions

    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
    ven
    -0.06
    apt
    -0.06
    bout
    -0.06
     Greenwood
    -0.06
    engo
    -0.05
     using
    -0.05
    akte
    -0.05
     road
    -0.05
    igne
    -0.05
     incom
    -0.05
    POSITIVE LOGITS
    yal
    0.08
    ovky
    0.08
    otel
    0.07
     cez
    0.07
    Å¡etÅĻenÃŃ
    0.07
    bsites
    0.07
    abox
    0.07
    ÙĨاÙĨ
    0.07
    UGE
    0.07
    chunks
    0.07
    Activations Density 0.024%

    No Known Activations