© 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. 125943
    Prev
    Next
    INDEX
    Explanations

    terms related to mortality rates and death statistics

    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
    -ahead
    -0.08
    ارÙĩ
    -0.07
     ÙĦÙĥرة
    -0.07
    olated
    -0.07
    nes
    -0.07
    ENO
    -0.07
    forth
    -0.07
    ness
    -0.06
    esta
    -0.06
    ãĥĬãĥ«
    -0.06
    POSITIVE LOGITS
     rate
    0.10
     rates
    0.10
    çİĩ
    0.09
    -rate
    0.08
    entai
    0.08
    quez
    0.08
    rate
    0.07
    erate
    0.07
    _rates
    0.07
    _rate
    0.06
    Activations Density 0.007%

    No Known Activations