© 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. 9-LLAMASCOPE-RES-131K
    11. 95315
    Prev
    Next
    INDEX
    Explanations

    marked up HTML or component-based syntax elements

    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
    reu
    -0.08
    lass
    -0.07
    unami
    -0.07
    anter
    -0.07
    itary
    -0.07
    orks
    -0.07
    engo
    -0.06
    ely
    -0.06
    er
    -0.06
     ActiveForm
    -0.06
    POSITIVE LOGITS
     Rooney
    0.06
    OID
    0.06
    ména
    0.06
    ãĥ¼ãĥĦ
    0.06
    Marco
    0.06
    _bundle
    0.06
     ACTIONS
    0.05
    otope
    0.05
     Rail
    0.05
    \Schema
    0.05
    Activations Density 0.023%

    No Known Activations