© 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. 118600
    Prev
    Next
    INDEX
    Explanations

    references to life and death related events or themes

    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
    ulong
    -0.07
    riet
    -0.07
    iet
    -0.07
    åĬŁ
    -0.06
     duro
    -0.06
     bay
    -0.06
    assy
    -0.06
    lion
    -0.06
    stance
    -0.06
    ngle
    -0.06
    POSITIVE LOGITS
     lives
    0.16
     Lives
    0.13
     life
    0.13
     жиÑĤÑĤÑı
    0.12
    çĶŁåij½
    0.12
     Leben
    0.11
    life
    0.11
     жизни
    0.11
    _life
    0.10
     жизнÑĮ
    0.10
    Activations Density 0.045%

    No Known Activations