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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1050
    Prev
    Next
    INDEX
    Explanations

    terms related to mindfulness and embodiment practices

    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
    thr
    -0.07
    ifr
    -0.07
    chu
    -0.07
    tridge
    -0.07
    axy
    -0.06
    UDO
    -0.06
    kara
    -0.06
    zm
    -0.06
    atile
    -0.06
    /page
    -0.06
    POSITIVE LOGITS
    fulness
    0.08
    -aware
    0.08
    ously
    0.07
    -Based
    0.07
    -based
    0.07
    ponge
    0.07
    plusplus
    0.06
    aware
    0.06
     aware
    0.06
     yoga
    0.06
    Activations Density 0.002%

    No Known Activations