© 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. 22-LLAMASCOPE-RES-131K
    11. 4313
    Prev
    Next
    INDEX
    Explanations

    technical terms related to materials science and semiconductor manufacturing

    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
    rowse
    -0.06
    Caps
    -0.06
     folding
    -0.06
    coil
    -0.06
    ettle
    -0.06
     tran
    -0.06
     permission
    -0.05
     privileges
    -0.05
     privilege
    -0.05
    é³´
    -0.05
    POSITIVE LOGITS
    Patterns
    0.11
     Mask
    0.11
     mask
    0.10
     Patterns
    0.10
    -mask
    0.10
     Masks
    0.10
     MASK
    0.09
     masks
    0.09
    mask
    0.09
     Pattern
    0.09
    Activations Density 0.018%

    No Known Activations