© 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. 83996
    Prev
    Next
    INDEX
    Explanations

    terms related to death or mortality

    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
    åŀ
    -0.06
    оÑĢоÑĤ
    -0.06
    .tc
    -0.06
    одÑĭ
    -0.06
    jay
    -0.06
     Russo
    -0.06
    iry
    -0.06
    .ExecuteScalar
    -0.06
    thur
    -0.06
     autorelease
    -0.06
    POSITIVE LOGITS
    -placeholder
    0.07
    äºİ
    0.07
    zion
    0.06
    εÏĢ
    0.06
    ISP
    0.06
    PCM
    0.06
    æĸ¼
    0.06
    raki
    0.06
    esch
    0.06
    eyed
    0.06
    Activations Density 0.001%

    No Known Activations