© 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. 42141
    Prev
    Next
    INDEX
    Explanations

    URLs or links related to M1 Garand rifles

    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
    arella
    -0.08
    ince
    -0.07
    IMP
    -0.07
    riding
    -0.06
    ÏĦηÏĤ
    -0.06
    inos
    -0.06
    uido
    -0.06
    -spin
    -0.06
    uart
    -0.06
    byt
    -0.06
    POSITIVE LOGITS
     showc
    0.06
     Petite
    0.06
    ramer
    0.06
     Addison
    0.06
     Yun
    0.06
     Fior
    0.06
    .addTo
    0.06
    ERE
    0.06
    ruz
    0.06
    cle
    0.06
    Activations Density 0.003%

    No Known Activations