© 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. 15-LLAMASCOPE-RES-131K
    11. 104324
    Prev
    Next
    INDEX
    Explanations

    recurring phrases and connectors in sentence structure

    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
    alars
    -0.08
    eger
    -0.07
    Äħd
    -0.07
    loquent
    -0.07
    çĴ
    -0.07
    phis
    -0.07
    ovie
    -0.07
    æ±Ł
    -0.07
    .struct
    -0.07
    echa
    -0.07
    POSITIVE LOGITS
     which
    0.06
     meaning
    0.06
    ivo
    0.06
     Lip
    0.06
    ased
    0.06
    ute
    0.06
     Migration
    0.06
     srand
    0.05
    ot
    0.05
     deals
    0.05
    Activations Density 0.029%

    No Known Activations