© 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 EvalsExportsinterp-engineNEWAPI 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. 104321
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving rewards or benefits

    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
    orio
    -0.08
    念
    -0.07
    ader
    -0.07
    åĢĻ
    -0.07
    ãĥ§
    -0.07
    اد
    -0.07
    lobal
    -0.07
    partners
    -0.06
    verse
    -0.06
    аÑĤÑĭ
    -0.06
    POSITIVE LOGITS
    pearance
    0.10
     benefits
    0.10
     rewards
    0.08
    itan
    0.08
     benefit
    0.08
     Benefits
    0.08
    portion
    0.07
     success
    0.07
    plied
    0.06
     advantages
    0.06
    Activations Density 0.002%

    No Known Activations