© 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. 26953
    Prev
    Next
    INDEX
    Explanations

    discussions centered around emotional and spiritual 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
     spot
    -0.06
     phantom
    -0.06
     ke
    -0.06
    zen
    -0.06
     passing
    -0.05
     hot
    -0.05
     .
    -0.05
     vice
    -0.05
     Switch
    -0.05
     last
    -0.05
    POSITIVE LOGITS
    ledon
    0.09
    iosa
    0.08
    ushima
    0.08
    коÑĤ
    0.08
    ascar
    0.07
    GridColumn
    0.07
    ÑĤеÑĢн
    0.07
    ÑĪка
    0.07
     ìĪł
    0.07
    theast
    0.07
    Activations Density 0.003%

    No Known Activations