© 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. 83180
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to partnerships and judicial influence

    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
    exampleInput
    -0.07
     determ
    -0.07
     Exit
    -0.07
    landa
    -0.06
    ellen
    -0.06
    elas
    -0.06
    aty
    -0.06
    rones
    -0.06
     determin
    -0.06
    heroes
    -0.06
    POSITIVE LOGITS
     action
    0.09
    action
    0.09
     something
    0.08
     actions
    0.07
    -action
    0.07
    ActionResult
    0.07
    (action
    0.07
    actions
    0.06
     ACTION
    0.06
    osi
    0.06
    Activations Density 0.018%

    No Known Activations