Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5435
    Prev
    Next
    INDEX
    Explanations

    references to wildlife conservation efforts

    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
     Worker
    -0.06
     Workers
    -0.06
     Kushner
    -0.06
    _tensors
    -0.06
    vale
    -0.06
     workers
    -0.06
     ph
    -0.06
     Beach
    -0.06
    Workers
    -0.05
     Bicycle
    -0.05
    POSITIVE LOGITS
     hunting
    0.11
     hunters
    0.10
     hunter
    0.10
    Outdoor
    0.10
     outdoors
    0.09
     Outdoor
    0.09
     angl
    0.09
     fishing
    0.09
     outf
    0.08
    ICAST
    0.08
    Activations Density 0.011%

    No Known Activations