© 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. 118638
    Prev
    Next
    INDEX
    Explanations

    themes related to climate change and international cooperation

    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
    anje
    -0.08
     @"↵
    -0.07
    edl
    -0.07
    isko
    -0.07
    ruba
    -0.07
    esco
    -0.07
    .Toolkit
    -0.07
    acho
    -0.07
     summ
    -0.07
    ksam
    -0.07
    POSITIVE LOGITS
     nationals
    0.06
    ije
    0.06
     Transit
    0.06
     marque
    0.06
     Miles
    0.06
    278
    0.05
     sensation
    0.05
     shall
    0.05
    :↵
    0.05
     Neuroscience
    0.05
    Activations Density 0.010%

    No Known Activations