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. 96193
    Prev
    Next
    INDEX
    Explanations

    terms related to sports statistics and game metrics

    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
     critical
    -0.07
    OrFail
    -0.06
    raya
    -0.06
    critical
    -0.06
     sight
    -0.06
    .tie
    -0.06
    untlet
    -0.06
    ucus
    -0.06
     Uy
    -0.06
    .printStackTrace
    -0.06
    POSITIVE LOGITS
    mn
    0.07
    rians
    0.07
    íijľ
    0.07
    ãĥģãĥ¥
    0.07
    еÑĩно
    0.06
    íĺķ
    0.06
    umb
    0.06
    ãĥ¼ãĥĵ
    0.06
    829
    0.06
    ÑĥменÑĤ
    0.06
    Activations Density 0.001%

    No Known Activations