© 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. 118952
    Prev
    Next
    INDEX
    Explanations

    terms related to geological and environmental processes

    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
    iw
    -0.07
    åĻ¨
    -0.06
    slash
    -0.06
    dera
    -0.06
    ment
    -0.06
    à¸Ĺร
    -0.06
    cou
    -0.06
    juan
    -0.06
    æ³
    -0.06
    esel
    -0.06
    POSITIVE LOGITS
    åİĭ
    0.10
     pressure
    0.10
     pressures
    0.09
     compression
    0.09
    å£ĵ
    0.09
    pressure
    0.09
    -pressure
    0.09
    compression
    0.09
     Pressure
    0.09
     compress
    0.08
    Activations Density 0.029%

    No Known Activations