© 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. 77985
    Prev
    Next
    INDEX
    Explanations

    historical references and military formations

    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
     extrad
    -0.07
    aney
    -0.06
    صد
    -0.06
    iju
    -0.06
     Rut
    -0.06
    ÑĢÑĥж
    -0.06
    declaring
    -0.06
     proc
    -0.06
    RelativeTo
    -0.06
    onium
    -0.06
    POSITIVE LOGITS
     lineage
    0.07
     absorbing
    0.07
     Demp
    0.06
    ldr
    0.06
    ç·¨
    0.06
     absorb
    0.06
    103
    0.06
    conte
    0.06
    ller
    0.06
    oton
    0.06
    Activations Density 0.010%

    No Known Activations