© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89877
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "and" along with related concepts or terms

    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
    osg
    -0.07
    ulton
    -0.07
    Bomb
    -0.07
    égor
    -0.07
    endale
    -0.07
    ̣
    -0.07
    /cop
    -0.07
    кÑĥп
    -0.07
    EGIN
    -0.07
    iddet
    -0.07
    POSITIVE LOGITS
    amp
    0.06
     implications
    0.06
     beyond
    0.06
    etz
    0.06
    anners
    0.06
    ena
    0.06
     implication
    0.06
    ider
    0.06
    -ish
    0.05
     Whit
    0.05
    Activations Density 0.020%

    No Known Activations