© 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. 84461
    Prev
    Next
    INDEX
    Explanations

    phrases related to funerals and the memorialization of deceased individuals

    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
    viso
    -0.07
    solete
    -0.06
    Įĵ
    -0.06
    arefa
    -0.06
     suppl
    -0.06
    916
    -0.06
     allegiance
    -0.06
    atori
    -0.06
     sup
    -0.06
    .raises
    -0.06
    POSITIVE LOGITS
     ashes
    0.10
    ashes
    0.09
     crem
    0.08
     scattering
    0.07
    keh
    0.07
    scatter
    0.07
     ash
    0.07
     кÑĢем
    0.07
     scatter
    0.07
    ackle
    0.07
    Activations Density 0.004%

    No Known Activations