© 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. 119071
    Prev
    Next
    INDEX
    Explanations

    references to funerals or related topics

    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
    asca
    -0.09
    ãĥ
    -0.09
    Ìī
    -0.08
     ëĭ¤ìļ´ë°Ľê¸°
    -0.08
    KIT
    -0.08
    ëį°ìĿ´íĬ¸
    -0.08
    istrovstvÃŃ
    -0.08
    ê±°ëŀĺê°Ģ
    -0.08
    iento
    -0.07
     Sesso
    -0.07
    POSITIVE LOGITS
     flat
    0.07
    nar
    0.06
    .metamodel
    0.06
    ocom
    0.06
    asz
    0.06
     -
    0.05
    uls
    0.05
     Sever
    0.05
     delivery
    0.05
     wid
    0.05
    Activations Density 0.000%

    No Known Activations