© 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. 128937
    Prev
    Next
    INDEX
    Explanations

    instances of engagement or commentary in online content

    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
    ego
    -0.08
    aho
    -0.08
    atica
    -0.08
    ragon
    -0.08
    ancell
    -0.08
    PCS
    -0.07
    egie
    -0.07
    .esp
    -0.07
    ienes
    -0.07
    efa
    -0.07
    POSITIVE LOGITS
    olle
    0.07
    /xhtml
    0.06
     Confeder
    0.06
     ignor
    0.06
     sez
    0.06
    olio
    0.05
     important
    0.05
     Carey
    0.05
     paint
    0.05
    ooled
    0.05
    Activations Density 0.000%

    No Known Activations