© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 94161
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitions that indicate contrasting ideas or nuances in arguments

    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
    å°ij
    -0.07
    aben
    -0.07
     Schro
    -0.06
    .Ptr
    -0.06
    URT
    -0.06
    ÙĴس
    -0.06
     absent
    -0.06
    .tk
    -0.06
    ANTLR
    -0.06
    dia
    -0.06
    POSITIVE LOGITS
    irk
    0.08
    nel
    0.07
    imon
    0.07
     Dawson
    0.07
    isto
    0.06
    LC
    0.06
     transit
    0.06
    %M
    0.06
     significant
    0.06
    ane
    0.06
    Activations Density 0.005%

    No Known Activations