© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26567
    Prev
    Next
    INDEX
    Explanations

    terms related to activated carbon and its applications

    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
    ja
    -0.08
    ailles
    -0.07
     largo
    -0.06
     undermin
    -0.06
    mit
    -0.06
     Cort
    -0.06
    rgb
    -0.06
    ounge
    -0.06
    COND
    -0.06
     Congress
    -0.06
    POSITIVE LOGITS
    оваÑĢ
    0.08
    axter
    0.07
     holding
    0.07
    inaire
    0.07
    /bind
    0.07
    PUR
    0.06
    еб
    0.06
    achu
    0.06
    gettext
    0.06
     interception
    0.06
    Activations Density 0.010%

    No Known Activations