© 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. 56531
    Prev
    Next
    INDEX
    Explanations

    expressions of limitations and impossibilities in relation to existence and belief

    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
    çıį
    -0.08
    ellas
    -0.07
    มà¸ķ
    -0.07
    ccione
    -0.07
    ego
    -0.07
    ugg
    -0.06
    ancel
    -0.06
     Nová
    -0.06
    iphy
    -0.06
    igel
    -0.06
    POSITIVE LOGITS
     unless
    0.08
     without
    0.08
     simultaneously
    0.08
     simultaneous
    0.07
    avicon
    0.07
    without
    0.06
    unless
    0.06
     any
    0.06
     sustained
    0.06
    à¹ĥà¸Ķ
    0.06
    Activations Density 0.031%

    No Known Activations