© 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 EvalsExportsinterp-engineNEWAPI 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. 95622
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental issues and social contexts

    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
    enga
    -0.07
    ync
    -0.07
    olib
    -0.06
    êt
    -0.06
    cion
    -0.06
    ancellable
    -0.06
    agne
    -0.06
    ç¸
    -0.05
    ason
    -0.05
     Frequ
    -0.05
    POSITIVE LOGITS
    ozem
    0.08
     prospect
    0.08
    apon
    0.07
     AssemblyVersion
    0.07
    ardon
    0.07
    erva
    0.06
    amel
    0.06
     Cop
    0.06
    ahr
    0.06
    ammer
    0.06
    Activations Density 0.063%

    No Known Activations