© 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. 15-LLAMASCOPE-RES-131K
    11. 62115
    Prev
    Next
    INDEX
    Explanations

    references to military ranks and official commands

    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
    anche
    -0.07
    ÃŃky
    -0.07
    mtime
    -0.07
    izik
    -0.07
    enek
    -0.07
    uros
    -0.07
    illian
    -0.06
     worker
    -0.06
    /inet
    -0.06
    UILD
    -0.06
    POSITIVE LOGITS
     Slov
    0.07
     Supply
    0.06
     alma
    0.06
    Supply
    0.06
     Weinstein
    0.06
     suic
    0.06
    son
    0.05
    bling
    0.05
    ven
    0.05
    610
    0.05
    Activations Density 0.026%

    No Known Activations