© 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. 127941
    Prev
    Next
    INDEX
    Explanations

    elements of nostalgia and idealized portrayals of relationships

    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
     se
    -0.07
    _prefs
    -0.06
    âłĢ
    -0.06
     ung
    -0.06
    anos
    -0.06
    unga
    -0.06
    twig
    -0.06
    eydi
    -0.05
     tin
    -0.05
    /preferences
    -0.05
    POSITIVE LOGITS
     benign
    0.09
     optimism
    0.09
     optimistic
    0.08
    optim
    0.08
    ideal
    0.08
     sugar
    0.08
     sunny
    0.08
     sunshine
    0.08
     innocent
    0.08
     gloss
    0.08
    Activations Density 0.046%

    No Known Activations