© 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. 9-LLAMASCOPE-RES-131K
    11. 95455
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly those with the name "Paul."

    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
    tplib
    -0.07
    lassian
    -0.07
    UIAlertAction
    -0.07
    istrat
    -0.07
     TMPro
    -0.07
    icut
    -0.06
    onica
    -0.06
    éré
    -0.06
    oda
    -0.06
    FETCH
    -0.06
    POSITIVE LOGITS
    Fold
    0.07
     Fold
    0.07
     Ideal
    0.07
     folding
    0.06
     Gale
    0.06
     fold
    0.06
    fold
    0.06
    alia
    0.06
    ¤í
    0.06
    ching
    0.06
    Activations Density 0.002%

    No Known Activations