© 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. 17-LLAMASCOPE-RES-131K
    11. 61208
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and processes related to equations

    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
    pery
    -0.07
    anke
    -0.07
    ritel
    -0.07
    ảm
    -0.07
    anger
    -0.07
    åı£
    -0.07
    åĨµ
    -0.07
    γκα
    -0.07
    _fc
    -0.07
    è¦
    -0.06
    POSITIVE LOGITS
    Ùİا
    0.07
     twice
    0.07
    맨
    0.06
    ANGLES
    0.06
    ement
    0.06
    ény
    0.06
    upp
    0.06
    äºĨä¸Ģ
    0.06
     heterogeneous
    0.05
    ORIZ
    0.05
    Activations Density 0.119%

    No Known Activations