© 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. 16577
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant challenges or boundary-breaking situations

    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
    idi
    -0.08
    rique
    -0.07
    elson
    -0.07
    IDL
    -0.07
    egers
    -0.06
    teri
    -0.06
    ivalent
    -0.06
    beck
    -0.06
    .ali
    -0.06
    ãĤ¦ãĤ¹
    -0.06
    POSITIVE LOGITS
     apart
    0.09
     deadlock
    0.09
     breaks
    0.08
    -breaking
    0.08
     breaking
    0.08
     break
    0.08
     broke
    0.08
     Breaking
    0.08
     tab
    0.08
    Breaking
    0.08
    Activations Density 0.030%

    No Known Activations