© 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. 40117
    Prev
    Next
    INDEX
    Explanations

    references to a divine or moral authority guiding behavior and support

    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
    æķ¦
    -0.06
     ap
    -0.06
     ult
    -0.06
    [Double
    -0.06
    isy
    -0.06
    ix
    -0.06
    &view
    -0.06
    878
    -0.06
    sto
    -0.06
    ãĥĨãĤ£
    -0.05
    POSITIVE LOGITS
    celain
    0.08
     Kemp
    0.07
    mono
    0.07
    strup
    0.07
    ltra
    0.07
    herits
    0.07
    iegel
    0.07
    гÑĥ
    0.07
    ìĥ
    0.07
     Morton
    0.07
    Activations Density 0.001%

    No Known Activations