© 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. 119475
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to border-radius values

    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
    zone
    -0.07
    viz
    -0.07
    strand
    -0.06
    wrapped
    -0.06
    ensa
    -0.06
     zone
    -0.06
     Hue
    -0.06
    æ²¢
    -0.06
    caled
    -0.06
    .Target
    -0.06
    POSITIVE LOGITS
     BorderRadius
    0.12
     rounding
    0.12
    .circular
    0.10
    -round
    0.10
    rounded
    0.10
     rounded
    0.10
     borderRadius
    0.10
     Round
    0.10
     ROUND
    0.09
    -rounded
    0.09
    Activations Density 0.007%

    No Known Activations