© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61198
    Prev
    Next
    INDEX
    Explanations

    phrases about engagement, responsibility, and the exchange of ideas or value

    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
    azo
    -0.08
    eos
    -0.08
    otech
    -0.07
    .VisualBasic
    -0.07
    hti
    -0.07
    afa
    -0.07
    DAQ
    -0.07
    ÏĦολ
    -0.07
    antan
    -0.07
    eni
    -0.07
    POSITIVE LOGITS
     those
    0.11
     Äijó
    0.09
    ãĢģãģĿãģ®
    0.09
     Those
    0.09
     that
    0.09
    éĤ£ä¸ª
    0.09
     tersebut
    0.08
    those
    0.08
     THAT
    0.08
    Those
    0.08
    Activations Density 0.050%

    No Known Activations