© 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. 5-LLAMASCOPE-RES-131K
    11. 125557
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Speaking" in various contexts

    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
    pcs
    -0.06
    iale
    -0.06
    aml
    -0.06
    ople
    -0.06
    ranÃŃ
    -0.05
    ional
    -0.05
    arch
    -0.05
     equalTo
    -0.05
    pu
    -0.05
    land
    -0.05
    POSITIVE LOGITS
    ://%
    0.07
    /datatables
    0.07
     Berm
    0.07
    /tutorial
    0.07
    rame
    0.07
    entai
    0.07
    apter
    0.07
    ħ§
    0.06
    allery
    0.06
     porr
    0.06
    Activations Density 0.002%

    No Known Activations