© 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. 54869
    Prev
    Next
    INDEX
    Explanations

    contractions and conditional phrases relating to opinions and uncertainty

    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
    ses
    -0.06
    lun
    -0.06
    @g
    -0.06
    orem
    -0.06
    641
    -0.05
     Touch
    -0.05
    вод
    -0.05
    q
    -0.05
    å±
    -0.05
    Touch
    -0.05
    POSITIVE LOGITS
    arded
    0.08
     geschichten
    0.08
    ossal
    0.07
     rfl
    0.07
    nero
    0.07
     Erotische
    0.07
    iales
    0.07
    çĦ¡ãģĹãģ
    0.07
     happening
    0.07
     dejtings
    0.07
    Activations Density 0.071%

    No Known Activations