© 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. 9-LLAMASCOPE-RES-131K
    11. 98541
    Prev
    Next
    INDEX
    Explanations

    geographical terms or features related to landscapes and elevations

    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
    aeper
    -0.07
    agua
    -0.07
    wers
    -0.06
    chied
    -0.06
    orners
    -0.06
    chez
    -0.06
    essler
    -0.06
    tring
    -0.06
    richt
    -0.06
    VERBOSE
    -0.06
    POSITIVE LOGITS
    ears
    0.07
    ear
    0.06
     dah
    0.06
     Spiele
    0.06
    NAL
    0.06
    -banner
    0.06
    .gmail
    0.06
    éłħ
    0.06
    .scalablytyped
    0.06
    Neighbor
    0.06
    Activations Density 0.005%

    No Known Activations