© 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. 15-LLAMASCOPE-RES-131K
    11. 87012
    Prev
    Next
    INDEX
    Explanations

    connections to historical events and contemporary issues

    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
    Anchor
    -0.07
    GuidId
    -0.07
    rei
    -0.07
    HeaderCode
    -0.07
    spb
    -0.07
    anged
    -0.07
     Erotische
    -0.07
     salopes
    -0.07
     Exped
    -0.07
    ëĦIJ
    -0.06
    POSITIVE LOGITS
     original
    0.12
     old
    0.09
     ORIGINAL
    0.09
    original
    0.09
     originals
    0.08
     Original
    0.08
    -original
    0.08
     originally
    0.08
     decades
    0.08
    Original
    0.07
    Activations Density 0.029%

    No Known Activations