© 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. 119558
    Prev
    Next
    INDEX
    Explanations

    references to significant life events, particularly weddings and personal experiences

    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
    oston
    -0.06
     é¦
    -0.06
    ennen
    -0.06
     also
    -0.06
    istine
    -0.06
    corp
    -0.06
    ault
    -0.06
    966
    -0.06
    ãģ¨ãĤĤ
    -0.06
    è¿ĺæľī
    -0.06
    POSITIVE LOGITS
     such
    0.15
     Such
    0.14
    Such
    0.13
     SUCH
    0.13
    such
    0.13
    è¿Ļæł·çļĦ
    0.12
     accordingly
    0.12
    è¿Ļç§į
    0.11
     takové
    0.10
    ãģĿãģĨ
    0.10
    Activations Density 0.095%

    No Known Activations