© 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. 85857
    Prev
    Next
    INDEX
    Explanations

    references to transactions or events involving sales

    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
    eyh
    -0.07
    aln
    -0.07
    cad
    -0.07
     Kuzey
    -0.07
    .lesson
    -0.07
     instantiate
    -0.07
    QUIRE
    -0.06
     вÑģпом
    -0.06
    Guardar
    -0.06
    ики
    -0.06
    POSITIVE LOGITS
     aforementioned
    0.07
    agal
    0.06
    157
    0.06
    237
    0.06
    âĶĺ
    0.06
    horn
    0.06
     âĨĵ
    0.06
    quet
    0.06
    -lnd
    0.05
     Vega
    0.05
    Activations Density 0.000%

    No Known Activations