© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2665
    Prev
    Next
    INDEX
    Explanations

    phrases conveying existence and identity, particularly in relation to complex social or interpersonal themes

    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
    ummings
    -0.07
    arine
    -0.07
     misd
    -0.07
    æºĢ
    -0.07
     tiener
    -0.07
    FromClass
    -0.07
     nackte
    -0.07
    wart
    -0.07
    ivant
    -0.07
    è¦
    -0.07
    POSITIVE LOGITS
     existence
    0.14
     exists
    0.13
     exist
    0.12
    exists
    0.10
    åŃĺåľ¨
    0.10
    existence
    0.10
     existe
    0.10
     existed
    0.10
     Exists
    0.10
     Exist
    0.10
    Activations Density 0.081%

    No Known Activations