© 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. 130678
    Prev
    Next
    INDEX
    Explanations

    information about cruise ships and their features

    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
    zej
    -0.07
     Kub
    -0.06
    icus
    -0.06
     sund
    -0.06
    OBJ
    -0.06
     patch
    -0.06
    bine
    -0.06
    ubah
    -0.05
    dur
    -0.05
     Moved
    -0.05
    POSITIVE LOGITS
     sisters
    0.08
    âĦĸâĦĸ
    0.07
     Trev
    0.07
     prototypes
    0.07
     nieu
    0.07
     Ú©ÙĦاس
    0.07
    ix
    0.07
     Sınıf
    0.07
    طار
    0.07
     manufact
    0.07
    Activations Density 0.038%

    No Known Activations