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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5198
    Prev
    Next
    INDEX
    Explanations

    interactions among groups of people

    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
    chet
    -0.08
    ãĥ³ãĥķ
    -0.07
    oku
    -0.07
    anko
    -0.07
    ucher
    -0.07
    åħ¼
    -0.07
    .SIG
    -0.07
    holm
    -0.07
    ullet
    -0.07
    ÑĨенÑĤÑĢа
    -0.07
    POSITIVE LOGITS
     surrounding
    0.11
     around
    0.10
     collective
    0.10
     milling
    0.09
     themselves
    0.09
     forming
    0.09
     surround
    0.09
     circle
    0.08
     collectively
    0.08
     formed
    0.08
    Activations Density 0.111%

    No Known Activations