© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95914
    Prev
    Next
    INDEX
    Explanations

    references to cameos or appearances of characters in media, particularly in a nostalgic or reunion 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
    Ñĸп
    -0.09
    ÑĨÑİ
    -0.07
    ccb
    -0.07
    INET
    -0.07
     åıĮ线
    -0.07
     actionTypes
    -0.07
    âī¡âī¡
    -0.07
    иÑģк
    -0.07
    hare
    -0.07
    imdi
    -0.07
    POSITIVE LOGITS
    cipher
    0.06
    bast
    0.06
     let
    0.06
    recht
    0.06
     conf
    0.06
     ver
    0.06
     guest
    0.06
     sp
    0.06
     re
    0.06
    angan
    0.05
    Activations Density 0.136%

    No Known Activations