© 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. 75379
    Prev
    Next
    INDEX
    Explanations

    phrases related to death and mourning

    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
    ici
    -0.07
    alous
    -0.07
     vot
    -0.07
    omed
    -0.07
    enz
    -0.07
     Thr
    -0.06
     Attr
    -0.06
    ritz
    -0.06
    anine
    -0.06
     Asi
    -0.06
    POSITIVE LOGITS
    ÛĮاÙĨ
    0.06
    Ħìŀ¬
    0.06
    oji
    0.06
    Lint
    0.06
    acyj
    0.06
    zee
    0.06
    ¸ı
    0.06
    bash
    0.06
    allel
    0.06
     taper
    0.05
    Activations Density 0.005%

    No Known Activations