© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 86048
    Prev
    Next
    INDEX
    Explanations

    elements related to speculative or hypothetical scenarios, particularly those involving financial constructs

    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
     wich
    -0.07
    aya
    -0.07
     etc
    -0.07
    asar
    -0.07
    )prepare
    -0.07
     unavoid
    -0.06
     hypothetical
    -0.06
    íĥģ
    -0.05
    obody
    -0.05
    Alright
    -0.05
    POSITIVE LOGITS
    enen
    0.07
    urat
    0.07
    cq
    0.07
    ãĢĤ↵↵↵↵↵↵
    0.07
    .pen
    0.06
    ylko
    0.06
     mav
    0.06
    .Safe
    0.06
    丸
    0.06
    lis
    0.06
    Activations Density 0.022%

    No Known Activations