© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3396
    Prev
    Next
    INDEX
    Explanations

    instances and descriptions associated with challenges and organizational complexity

    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
    849
    -0.07
     Verfügung
    -0.06
    fir
    -0.06
     observ
    -0.06
     Rug
    -0.06
    azer
    -0.06
    AVAILABLE
    -0.06
    ãĥĢãĥ¼
    -0.05
     vo
    -0.05
     rug
    -0.05
    POSITIVE LOGITS
     complexity
    0.13
    complex
    0.13
    _complex
    0.13
     Complex
    0.13
    Complex
    0.12
     complex
    0.12
     challenging
    0.11
     phức
    0.11
     demanding
    0.11
     Complexity
    0.11
    Activations Density 0.030%

    No Known Activations