© 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. 15-LLAMASCOPE-RES-131K
    11. 88451
    Prev
    Next
    INDEX
    Explanations

    keywords related to economic conditions and agricultural production

    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
    ose
    -0.06
    ockey
    -0.06
    iosper
    -0.06
    ibri
    -0.06
    ettel
    -0.06
    LEGRO
    -0.06
    itage
    -0.06
    DE
    -0.06
    isel
    -0.06
     summ
    -0.06
    POSITIVE LOGITS
    OwnerId
    0.07
     prat
    0.07
    aky
    0.07
    abase
    0.06
    agle
    0.06
    FFFFFFFF
    0.06
    fullscreen
    0.06
    nio
    0.06
    .eql
    0.06
    -highlight
    0.06
    Activations Density 0.005%

    No Known Activations