© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26817
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics

    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
    ãģıãĤĮ
    -0.07
     EÅŁ
    -0.07
    /Gate
    -0.07
    άÏĥ
    -0.07
    /conf
    -0.06
    ÑĪин
    -0.06
    krom
    -0.06
    ãģıãģł
    -0.06
     Kaiser
    -0.06
     Surre
    -0.06
    POSITIVE LOGITS
    PasswordEncoder
    0.06
    ije
    0.06
    ñ
    0.06
    570
    0.06
    好
    0.06
    ko
    0.05
    itch
    0.05
    å¼ı
    0.05
    DataType
    0.05
    aniu
    0.05
    Activations Density 0.000%

    No Known Activations