© 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. 30484
    Prev
    Next
    INDEX
    Explanations

    references to natural landscapes and outdoor adventures

    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
     pond
    -0.08
     Pond
    -0.07
    ãĤ¯ãĥĪ
    -0.07
    Lake
    -0.07
    lemetry
    -0.07
    ippi
    -0.07
    abbo
    -0.07
     Lakes
    -0.07
     Prairie
    -0.07
    udit
    -0.07
    POSITIVE LOGITS
     cliff
    0.09
     steep
    0.08
     mountain
    0.08
     hill
    0.07
     rock
    0.07
     climbing
    0.07
     stair
    0.07
    å²³
    0.06
    aje
    0.06
     terr
    0.06
    Activations Density 0.071%

    No Known Activations