© 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. 117784
    Prev
    Next
    INDEX
    Explanations

    recurring themes and patterns in context

    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
    ĮĢ
    -0.07
    rij
    -0.06
     hence
    -0.05
     spirits
    -0.05
     Matth
    -0.05
    wa
    -0.05
    cher
    -0.05
     prov
    -0.05
    jo
    -0.05
    wendung
    -0.05
    POSITIVE LOGITS
     because
    0.27
    because
    0.26
    Because
    0.22
     porque
    0.22
     Because
    0.22
    åĽłä¸º
    0.22
     omdat
    0.20
    ecause
    0.19
     karena
    0.19
    à¹Ģà¸ŀราะ
    0.19
    Activations Density 0.002%

    No Known Activations