© 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. 128603
    Prev
    Next
    INDEX
    Explanations

    words related to chemical concepts and terminology

    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
    ssize
    -0.07
    -ÑĤаки
    -0.07
    sert
    -0.07
    pole
    -0.07
     ethic
    -0.07
    uum
    -0.07
    Rib
    -0.07
    าย
    -0.07
     Trit
    -0.07
    ooth
    -0.07
    POSITIVE LOGITS
    istry
    0.08
    оÑĢаз
    0.08
    ichael
    0.07
    /engine
    0.07
    DebugEnabled
    0.06
    ISTRY
    0.06
    /math
    0.06
    å¸Ī
    0.06
    MF
    0.06
    룬ìĬ¤
    0.06
    Activations Density 0.012%

    No Known Activations