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. 9-LLAMASCOPE-RES-131K
    6. 96191
    Prev
    Next
    INDEX
    Explanations

    references to the game "Go" and related board games

    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
    UnderTest
    -0.06
     mastur
    -0.06
    altar
    -0.06
    blo
    -0.06
     доÑĤ
    -0.06
    uary
    -0.06
    âͬ
    -0.06
    ãĥ¼ãĥĬ
    -0.06
    -native
    -0.06
    LEC
    -0.06
    POSITIVE LOGITS
    berman
    0.08
    ayi
    0.07
    isti
    0.06
    cestor
    0.06
    afka
    0.06
    aney
    0.06
    abilit
    0.06
    ört
    0.06
    ÃŃt
    0.06
    antis
    0.06
    Activations Density 0.001%

    No Known Activations