© 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. 85813
    Prev
    Next
    INDEX
    Explanations

    monetary references or pricing information

    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
    deniz
    -0.07
    ĶĶ
    -0.06
    bench
    -0.06
    orners
    -0.06
     Branch
    -0.06
    incare
    -0.06
    enery
    -0.06
    ylland
    -0.06
     branch
    -0.06
     thermostat
    -0.06
    POSITIVE LOGITS
    hausen
    0.08
     Early
    0.08
     gates
    0.07
     Gate
    0.07
    Early
    0.07
     gate
    0.07
     ticket
    0.07
     ump
    0.06
    Gate
    0.06
     entry
    0.06
    Activations Density 0.010%

    No Known Activations