© 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. 57407
    Prev
    Next
    INDEX
    Explanations

    references to aerial photography and technology specifications

    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
     male
    -0.06
     female
    -0.06
    away
    -0.06
     Music
    -0.06
     breakdown
    -0.06
    MMC
    -0.05
    ij
    -0.05
    ad
    -0.05
     Genome
    -0.05
    938
    -0.05
    POSITIVE LOGITS
     Acquisition
    0.08
     acquisition
    0.08
     acquired
    0.08
    senal
    0.08
     imagery
    0.08
     acquisitions
    0.07
    odata
    0.07
    TypeDef
    0.07
    Temporal
    0.07
    Coverage
    0.07
    Activations Density 0.003%

    No Known Activations