© 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. 78752
    Prev
    Next
    INDEX
    Explanations

    relationships between companies and acquisitions

    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
    illas
    -0.07
    ettel
    -0.06
    rane
    -0.06
    asher
    -0.06
    ISR
    -0.06
     Twins
    -0.06
    ollower
    -0.05
     Jennings
    -0.05
    rana
    -0.05
     ÑĤва
    -0.05
    POSITIVE LOGITS
     parent
    0.13
    parent
    0.11
     Parent
    0.10
    -parent
    0.09
    Parent
    0.09
     ownership
    0.08
    	parent
    0.08
    ownership
    0.08
     owner
    0.08
    .parent
    0.08
    Activations Density 0.032%

    No Known Activations