© 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. 61522
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stop" and its variations in various contexts

    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
    cke
    -0.08
     basically
    -0.07
    anas
    -0.07
    gne
    -0.06
    ayo
    -0.06
    áty
    -0.06
    nze
    -0.06
    rchive
    -0.06
    igue
    -0.06
     deserving
    -0.06
    POSITIVE LOGITS
    STOP
    0.07
    fel
    0.07
    sik
    0.07
    ordin
    0.07
     eens
    0.06
    fad
    0.06
    isté
    0.06
    302
    0.06
     thÄĥm
    0.06
    leton
    0.06
    Activations Density 0.007%

    No Known Activations