© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 60335
    Prev
    Next
    INDEX
    Explanations

    expressions related to hiking and outdoor activities

    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
    olulu
    -0.06
     ÙģرÙĪ
    -0.06
     hills
    -0.06
     hill
    -0.06
    æł¼
    -0.06
    ibbon
    -0.06
    habi
    -0.06
    nder
    -0.06
    feof
    -0.06
    æķ´
    -0.05
    POSITIVE LOGITS
    Temporary
    0.08
     Temporary
    0.08
     saddle
    0.08
    temporary
    0.07
    è§Ħ模
    0.07
     tạm
    0.07
    _CONSTANT
    0.07
    ugg
    0.06
    виÑī
    0.06
    urname
    0.06
    Activations Density 0.025%

    No Known Activations