© 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. 3675
    Prev
    Next
    INDEX
    Explanations

    words and phrases that convey contrasts between positive and negative experiences

    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
    ãģĦãĤĭ
    -0.08
    å¾Ĵ
    -0.08
     nues
    -0.07
    λÏİ
    -0.07
    utsch
    -0.07
    алÑİ
    -0.07
    issy
    -0.07
    podob
    -0.07
    ossa
    -0.07
    bÃŃr
    -0.07
    POSITIVE LOGITS
    antages
    0.08
    otto
    0.06
    ara
    0.06
    (es
    0.06
    大åĪ©
    0.06
     ride
    0.06
    undred
    0.06
    ru
    0.06
     Lia
    0.05
    aware
    0.05
    Activations Density 0.003%

    No Known Activations