© 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. 123774
    Prev
    Next
    INDEX
    Explanations

    phrases related to existential conditions or states of being

    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
     downright
    -0.07
     Gee
    -0.07
    aroo
    -0.06
    nt
    -0.06
     Clayton
    -0.06
    382
    -0.06
    ao
    -0.06
    405
    -0.06
    ulous
    -0.06
    eer
    -0.06
    POSITIVE LOGITS
    iversit
    0.08
    ÌĨ
    0.07
    Lorem
    0.07
     adj
    0.07
    ÑĢеп
    0.07
    å·»
    0.07
    óng
    0.07
    etheless
    0.07
    ród
    0.07
    олÑĮ
    0.07
    Activations Density 0.008%

    No Known Activations