© 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. 57427
    Prev
    Next
    INDEX
    Explanations

    sentences that express a strong opinion or judgment

    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
    Trait
    -0.07
    erah
    -0.07
     downside
    -0.07
     albeit
    -0.07
    ansi
    -0.07
    arro
    -0.07
    raya
    -0.06
    âĸ¡
    -0.06
     although
    -0.06
    azes
    -0.06
    POSITIVE LOGITS
     nor
    0.11
     but
    0.11
     But
    0.09
     Nor
    0.09
    but
    0.08
    ï¼Įä½Ĩ
    0.08
     maar
    0.08
    But
    0.07
     но
    0.07
     íķĺì§Ģë§Į
    0.07
    Activations Density 0.028%

    No Known Activations