Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126603
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions and expressions of disbelief or frustration

    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
    owitz
    -0.08
    our
    -0.07
    utton
    -0.06
    ampil
    -0.06
    pard
    -0.06
     Kami
    -0.06
    arf
    -0.06
     OUR
    -0.06
    utes
    -0.06
    alla
    -0.06
    POSITIVE LOGITS
     OP
    0.07
    erece
    0.07
     sounds
    0.07
    alytics
    0.07
    _dispatcher
    0.06
     your
    0.06
     maduras
    0.06
     oto
    0.06
    OMPI
    0.06
     she
    0.06
    Activations Density 0.001%

    No Known Activations