© 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. 40173
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "break" and its variations

    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
    irth
    -0.08
    cki
    -0.08
    idi
    -0.08
    IDI
    -0.07
     Dispose
    -0.06
    elp
    -0.06
    ÑĤÑĮ
    -0.06
    uary
    -0.06
    ulings
    -0.06
    หา
    -0.06
    POSITIVE LOGITS
     breaking
    0.11
     Breaking
    0.10
     break
    0.10
    -breaking
    0.09
     breaker
    0.09
    Breaking
    0.09
    -break
    0.09
     broke
    0.09
     Break
    0.08
    breaking
    0.08
    Activations Density 0.018%

    No Known Activations