© 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. 57722
    Prev
    Next
    INDEX
    Explanations

    phrases related to preventative measures or actions

    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
    ноÑģи
    -0.09
    ndx
    -0.09
    .flink
    -0.08
    бав
    -0.07
    ↵↵
    -0.07
    .override
    -0.07
    acerb
    -0.07
    ä¸Ī
    -0.07
     बल
    -0.07
    itom
    -0.07
    POSITIVE LOGITS
     thereby
    0.10
     ultimately
    0.10
     later
    0.08
     hopefully
    0.07
     better
    0.07
     eventually
    0.07
     ultimate
    0.07
     Ultimately
    0.06
    ult
    0.06
    uard
    0.06
    Activations Density 0.038%

    No Known Activations