© 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. 74720
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specific instructions or suggested actions

    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
    sonian
    -0.06
    rain
    -0.06
    isted
    -0.06
    ble
    -0.06
     lẽ
    -0.06
     bedside
    -0.06
     θÎŃ
    -0.06
    egl
    -0.06
    intro
    -0.06
    inning
    -0.06
    POSITIVE LOGITS
    Å¡ak
    0.07
    ymoon
    0.07
    Ñįй
    0.07
    freeze
    0.07
    anism
    0.06
    arım
    0.06
    ç´Ļ
    0.06
    riba
    0.06
    ì¡°
    0.06
    머ëĭĪ
    0.06
    Activations Density 0.012%

    No Known Activations