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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 3569
    Prev
    Next
    INDEX
    Explanations

    expressions of clarity or statements of fact

    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
    addock
    -0.06
    amel
    -0.06
    Ħ
    -0.06
    alaxy
    -0.06
    aight
    -0.06
     exert
    -0.06
    /DD
    -0.06
    licate
    -0.06
    алог
    -0.06
    ellig
    -0.06
    POSITIVE LOGITS
    udo
    0.07
    datas
    0.07
    Feels
    0.07
     viewer
    0.07
    LBL
    0.07
    INCLUDED
    0.07
    reau
    0.07
    ãĤ¤ãĤº
    0.06
    ingen
    0.06
    FML
    0.06
    Activations Density 0.000%

    No Known Activations