© 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. 75434
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reasons or justifications

    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
    alles
    -0.07
    htt
    -0.06
    urum
    -0.06
    ermann
    -0.06
    olie
    -0.06
    .raise
    -0.06
    alte
    -0.06
    IOC
    -0.06
     Realm
    -0.06
    umbn
    -0.06
    POSITIVE LOGITS
     justified
    0.11
     warranted
    0.10
     rightly
    0.09
     indeed
    0.09
     deserved
    0.09
    reasonable
    0.09
    Reason
    0.09
    reason
    0.09
     understandable
    0.09
    çIJĨçĶ±
    0.09
    Activations Density 0.088%

    No Known Activations