© 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. 15-LLAMASCOPE-RES-131K
    6. 825
    Prev
    Next
    INDEX
    Explanations

    references to specific plants or flora

    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
     carc
    -0.06
    illet
    -0.06
    onas
    -0.06
     paint
    -0.06
     Leader
    -0.06
    udder
    -0.05
     dokun
    -0.05
    ContentView
    -0.05
    åĬ¨çī©
    -0.05
     flattering
    -0.05
    POSITIVE LOGITS
    .::
    0.07
    /TT
    0.07
    à¤Ĥà¤ľ
    0.07
    ulares
    0.07
     Rubio
    0.07
    .photos
    0.06
    untime
    0.06
    dess
    0.06
    اØŃÛĮ
    0.06
    ÑĤÑİ
    0.06
    Activations Density 0.004%

    No Known Activations