© 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. 74685
    Prev
    Next
    INDEX
    Explanations

    connections between economic trends and social dynamics

    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
    åıĬåħ¶
    -0.07
    ãģĿãģĵ
    -0.07
     ÙĪرز
    -0.07
    ]âĢı
    -0.07
    actionDate
    -0.07
     its
    -0.06
    ropoda
    -0.06
    .son
    -0.06
    riel
    -0.06
    ï½¢
    -0.06
    POSITIVE LOGITS
    alto
    0.09
     overall
    0.08
     etc
    0.08
     together
    0.07
    etc
    0.07
    overall
    0.07
     altogether
    0.07
     Overall
    0.07
    asse
    0.07
    —all
    0.07
    Activations Density 0.055%

    No Known Activations