© 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. 15-LLAMASCOPE-RES-131K
    11. 88261
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and statements

    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
    oi
    -0.07
    ab
    -0.06
    asar
    -0.06
    arent
    -0.06
    prech
    -0.06
    sono
    -0.06
    unma
    -0.06
    ssel
    -0.06
    ajo
    -0.06
    JK
    -0.06
    POSITIVE LOGITS
    anced
    0.07
    kul
    0.07
    LETTE
    0.07
    egin
    0.07
    θι
    0.06
    finish
    0.06
    -ever
    0.06
    ccione
    0.06
    /feed
    0.06
    zen
    0.06
    Activations Density 0.024%

    No Known Activations