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

    Neuronpedia

    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. 30131
    Prev
    Next
    INDEX
    Explanations

    terms related to political 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
    odo
    -0.07
    asin
    -0.07
    obo
    -0.07
    vyk
    -0.07
    case
    -0.06
     Stability
    -0.06
    oration
    -0.06
    -0.06
    bid
    -0.06
    's
    -0.06
    POSITIVE LOGITS
    dden
    0.08
     oriented
    0.08
    isch
    0.07
    Enums
    0.07
    ailable
    0.07
    izzato
    0.07
     hóa
    0.07
    .Percent
    0.07
     orient
    0.07
    /TT
    0.07
    Activations Density 0.051%

    No Known Activations