© 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. 31088
    Prev
    Next
    INDEX
    Explanations

    instances of terms related to trending topics and social media

    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
    aras
    -0.08
    ανδ
    -0.07
    ceed
    -0.07
    astos
    -0.07
    balanced
    -0.07
    aber
    -0.07
    ÏĦÏī
    -0.07
    ilden
    -0.07
    sak
    -0.07
    quier
    -0.06
    POSITIVE LOGITS
    ìłĢ
    0.06
    oon
    0.06
    ouce
    0.06
     Mer
    0.06
    Appearance
    0.06
    ë£
    0.06
    corner
    0.06
     Tem
    0.05
    aturing
    0.05
     spoken
    0.05
    Activations Density 0.002%

    No Known Activations