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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3972
    Prev
    Next
    INDEX
    Explanations

    instances of the word "see" in various contexts related to attendance and experiences

    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
     reife
    -0.07
    ãģĻãģIJ
    -0.07
    æĹģ
    -0.07
    ìm
    -0.07
    ILLA
    -0.07
    jom
    -0.07
    ạp
    -0.07
     tả
    -0.07
    APPER
    -0.07
    .scalablytyped
    -0.07
    POSITIVE LOGITS
     live
    0.08
     performances
    0.07
    live
    0.07
    andler
    0.06
     performance
    0.06
    Live
    0.06
    perform
    0.06
     sunset
    0.06
     at
    0.06
     je
    0.06
    Activations Density 0.025%

    No Known Activations