© 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. 61952
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming and data manipulation tasks

    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
    Ø®ÙĪاÙĨ
    -0.07
    mbH
    -0.07
    chu
    -0.07
    hoo
    -0.06
    icult
    -0.06
    /cop
    -0.06
    /generated
    -0.06
    екÑĤи
    -0.06
    ilinear
    -0.06
    wake
    -0.06
    POSITIVE LOGITS
     later
    0.09
    later
    0.08
    odo
    0.07
    azen
    0.07
     THEN
    0.07
    Later
    0.07
    379
    0.07
     subsequently
    0.07
    angan
    0.06
     Later
    0.06
    Activations Density 0.015%

    No Known Activations