© 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. 78435
    Prev
    Next
    INDEX
    Explanations

    details about properties and their unique 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
    Äįel
    -0.08
    ëĬIJ
    -0.07
    /cms
    -0.07
    åŃĺäºİ
    -0.07
    ldb
    -0.06
    ourke
    -0.06
    gnore
    -0.06
    biên
    -0.06
    иÑİ
    -0.06
     ours
    -0.06
    POSITIVE LOGITS
     quoi
    0.06
    610
    0.06
    ãĥ³ãĥī
    0.06
     entertainment
    0.06
    263
    0.06
    azen
    0.06
     giochi
    0.05
     jet
    0.05
     Punch
    0.05
     Rarity
    0.05
    Activations Density 0.008%

    No Known Activations