© 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. 127964
    Prev
    Next
    INDEX
    Explanations

    key phrases and concepts related to rights, freedoms, and social justice

    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
    interopRequire
    -0.08
    .appspot
    -0.07
    nelle
    -0.07
    bler
    -0.07
    ="{!!
    -0.06
    út
    -0.06
    andest
    -0.06
     onPostExecute
    -0.06
    engo
    -0.06
     Moreno
    -0.06
    POSITIVE LOGITS
    amas
    0.06
    Arena
    0.06
     Arena
    0.06
    uba
    0.06
    thesis
    0.06
    Pred
    0.06
    алеж
    0.06
    ucci
    0.06
    om
    0.06
     Craft
    0.06
    Activations Density 0.031%

    No Known Activations