© 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. 128799
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases about natural landscapes and geographical features

    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
    ulumi
    -0.08
    oshi
    -0.07
    ÑĢоÑĩ
    -0.07
    Å¡ek
    -0.07
     ApiResponse
    -0.07
    esser
    -0.07
    ãĥ³ãĥĦ
    -0.06
    emodel
    -0.06
    á»ı
    -0.06
     MediaType
    -0.06
    POSITIVE LOGITS
     habit
    0.06
     tip
    0.06
    jos
    0.06
     trans
    0.06
    rad
    0.06
    czy
    0.06
     rewards
    0.06
     abruptly
    0.06
     sea
    0.06
     minib
    0.05
    Activations Density 0.013%

    No Known Activations