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

    Neuronpedia

    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. 28701
    Prev
    Next
    INDEX
    Explanations

    associations with commitments and promises, particularly in regards to dishonoring agreements

    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
    voy
    -0.06
    azo
    -0.06
    ħ§
    -0.06
     gate
    -0.06
     Gate
    -0.06
     pup
    -0.06
    flux
    -0.06
     iso
    -0.06
    emploi
    -0.06
    ÎŃν
    -0.06
    POSITIVE LOGITS
     promises
    0.09
     commitments
    0.09
     honoring
    0.09
     obligations
    0.09
     Honor
    0.09
    hon
    0.08
     honor
    0.08
    åħ
    0.08
     integrity
    0.08
     obligation
    0.07
    Activations Density 0.030%

    No Known Activations