© 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. 85526
    Prev
    Next
    INDEX
    Explanations

    descriptive elements related to mountain scenery and experiences

    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
     river
    -0.10
     River
    -0.08
    river
    -0.08
    River
    -0.08
    æ²³
    -0.08
     bottom
    -0.07
     Rivers
    -0.07
     æ²³
    -0.07
     Bottom
    -0.06
     rivers
    -0.06
    POSITIVE LOGITS
    reward
    0.08
     summit
    0.08
    olar
    0.08
    Reward
    0.08
    peak
    0.07
     rewards
    0.07
    gard
    0.07
     reward
    0.07
     Reward
    0.07
     rewarding
    0.07
    Activations Density 0.020%

    No Known Activations