© 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. 77411
    Prev
    Next
    INDEX
    Explanations

    references to specific political figures and events

    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
    uber
    -0.07
    okit
    -0.07
    SOLE
    -0.06
    ÏĨοÏģ
    -0.06
    egin
    -0.06
    eson
    -0.06
    ìĿ´ëĵľ
    -0.06
    _resolve
    -0.06
    ombok
    -0.06
    affer
    -0.06
    POSITIVE LOGITS
     Seah
    0.07
    uv
    0.06
    .Conn
    0.06
    emu
    0.06
    rou
    0.06
    eter
    0.06
    ibu
    0.06
     Sey
    0.06
     Connector
    0.06
    (Collection
    0.06
    Activations Density 0.000%

    No Known Activations