© 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. 29491
    Prev
    Next
    INDEX
    Explanations

    elements related to technological and organizational structures

    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
    494
    -0.06
    dera
    -0.06
    berg
    -0.06
    akin
    -0.06
    ivos
    -0.06
    nave
    -0.06
     Mojo
    -0.06
    .attribute
    -0.06
    agle
    -0.06
    038
    -0.06
    POSITIVE LOGITS
     STDCALL
    0.07
    ë§Ŀ
    0.07
     tersebut
    0.07
    onis
    0.07
    /framework
    0.06
    inerary
    0.06
    ROWSER
    0.06
    åıĬåħ¶
    0.06
    SSIP
    0.06
    ÙĪÙĨÙĩ
    0.06
    Activations Density 0.058%

    No Known Activations