© 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. 73239
    Prev
    Next
    INDEX
    Explanations

    instances of similarity or repetition in contexts

    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
     Sunrise
    -0.06
    cook
    -0.06
    abin
    -0.06
    segue
    -0.06
    tere
    -0.06
    овÑĸд
    -0.06
    kee
    -0.06
     Russ
    -0.06
    -нибÑĥдÑĮ
    -0.05
     buff
    -0.05
    POSITIVE LOGITS
     year
    0.11
     month
    0.10
     годÑĥ
    0.08
     tahun
    0.08
    .year
    0.08
    month
    0.08
    year
    0.08
     jaar
    0.08
    627
    0.07
    å¹´
    0.07
    Activations Density 0.005%

    No Known Activations