© 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. 17-LLAMASCOPE-RES-131K
    11. 106750
    Prev
    Next
    INDEX
    Explanations

    terms related to UV lighting and products

    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
    -than
    -0.07
    877
    -0.06
     "
    -0.06
    389
    -0.06
    vido
    -0.05
     “
    -0.05
    Ùį
    -0.05
    als
    -0.05
    ruptcy
    -0.05
     GUIContent
    -0.05
    POSITIVE LOGITS
    ebek
    0.08
    rada
    0.08
    aģın
    0.07
    Ì
    0.07
    urette
    0.07
    rena
    0.07
    blr
    0.07
    ̣
    0.07
    inizin
    0.07
    eso
    0.07
    Activations Density 0.012%

    No Known Activations