© 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. 61950
    Prev
    Next
    INDEX
    Explanations

    terms related to journalism and military roles

    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
     benchmark
    -0.06
    Benchmark
    -0.06
    benchmark
    -0.06
    iller
    -0.06
     rex
    -0.06
     Benchmark
    -0.05
    ara
    -0.05
     block
    -0.05
    pta
    -0.05
    appen
    -0.05
    POSITIVE LOGITS
    _Field
    0.09
    field
    0.07
    leaf
    0.07
    strup
    0.07
    //{{
    0.07
    chy
    0.07
    .field
    0.07
     dolu
    0.07
     roadside
    0.07
     field
    0.07
    Activations Density 0.004%

    No Known Activations