© 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. 125783
    Prev
    Next
    INDEX
    Explanations

    references to love and personal connections within artistic expressions

    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
    .scalablytyped
    -0.08
    _MEDIA
    -0.08
    gı
    -0.08
    iddy
    -0.07
     valide
    -0.07
    ìĶĢ
    -0.07
    ãģ®æĸ¹
    -0.07
    )>>
    -0.07
    oui
    -0.07
     Leer
    -0.07
    POSITIVE LOGITS
     tomorrow
    0.06
     someday
    0.06
    âĢļ
    0.06
    arp
    0.05
     [
    0.05
    [e
    0.05
    __()
    0.05
     Alv
    0.05
    708
    0.05
    uted
    0.05
    Activations Density 0.141%

    No Known Activations