© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90361
    Prev
    Next
    INDEX
    Explanations

    elements related to archival or organizational features in content

    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
     Hacker
    -0.06
     Dit
    -0.06
     Farr
    -0.06
    ī´
    -0.05
     Tier
    -0.05
     åĤ
    -0.05
    cc
    -0.05
     Dale
    -0.05
     capacity
    -0.05
     Rails
    -0.05
    POSITIVE LOGITS
    CppClass
    0.08
    urma
    0.08
    rig
    0.08
    ARAM
    0.07
    usercontent
    0.07
    omap
    0.07
    jsonp
    0.07
    ksam
    0.07
    lder
    0.07
     ade
    0.07
    Activations Density 0.003%

    No Known Activations