© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 87546
    Prev
    Next
    INDEX
    Explanations

    phrases indicating impending trouble or consequences

    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
    iyan
    -0.07
    Slf
    -0.07
    irá
    -0.06
     Dra
    -0.06
     characteristic
    -0.06
    LAG
    -0.06
    stellung
    -0.06
    nett
    -0.06
     text
    -0.06
     Craft
    -0.06
    POSITIVE LOGITS
    æĹıèĩªæ²»
    0.06
     Tears
    0.06
     Tec
    0.06
    ifo
    0.06
    cot
    0.06
    atk
    0.06
    imo
    0.06
     Verified
    0.06
    à¸ķะ
    0.06
    åŃ
    0.06
    Activations Density 0.002%

    No Known Activations