© 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 EvalsExportsAPI 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. 57414
    Prev
    Next
    INDEX
    Explanations

    themes related to historical context and social commentary

    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
    hopefully
    -0.08
    ince
    -0.08
    -0.07
    onium
    -0.07
    _almost
    -0.07
    iamond
    -0.06
    /loader
    -0.06
    ame
    -0.06
     prostitu
    -0.06
    antis
    -0.06
    POSITIVE LOGITS
     however
    0.41
    however
    0.28
     However
    0.27
    However
    0.25
     jedoch
    0.24
     HOWEVER
    0.23
     однако
    0.23
     však
    0.22
     aber
    0.20
     allerdings
    0.19
    Activations Density 0.800%

    No Known Activations