© 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. 106869
    Prev
    Next
    INDEX
    Explanations

    expressions indicating conflict or contrasting situations

    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
    lds
    -0.08
    azu
    -0.07
    .scalablytyped
    -0.07
    ohana
    -0.07
     Gins
    -0.07
    ngine
    -0.07
    holm
    -0.06
    ãĤ¹ãĤ³
    -0.06
    neau
    -0.06
     Vlad
    -0.06
    POSITIVE LOGITS
     soon
    0.08
    soon
    0.07
    angan
    0.06
    ovel
    0.06
     Soon
    0.06
    ormal
    0.06
     underlying
    0.05
    oux
    0.05
     GURL
    0.05
    emark
    0.05
    Activations Density 0.009%

    No Known Activations