© 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. 128743
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic and industrial factors in a political context

    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
    regor
    -0.07
    å®
    -0.07
     tÅĻÃŃ
    -0.07
    abox
    -0.06
    spb
    -0.06
    循
    -0.06
    wor
    -0.06
    ÑĤÑĸ
    -0.06
    uv
    -0.06
    аÑĪа
    -0.06
    POSITIVE LOGITS
    /dc
    0.06
    λιά
    0.06
    acon
    0.06
    fty
    0.06
    frau
    0.06
     ERR
    0.06
    eel
    0.06
     helm
    0.06
    ptune
    0.06
     Retro
    0.06
    Activations Density 0.065%

    No Known Activations