© 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. 103903
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational tasks and work processes

    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
    Æ°
    -0.08
    RIPT
    -0.07
    égor
    -0.07
    είÏĦε
    -0.07
    ellas
    -0.07
    rzy
    -0.07
    /ws
    -0.07
     LAP
    -0.07
    oine
    -0.07
     karak
    -0.07
    POSITIVE LOGITS
     Samar
    0.06
    410
    0.06
    oman
    0.05
    ce
    0.05
     prose
    0.05
     yesterday
    0.05
     involving
    0.05
    ê³Ħ
    0.05
    umen
    0.05
     keycode
    0.05
    Activations Density 0.003%

    No Known Activations