© 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. 125712
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Delilah."

    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
    atore
    -0.07
    IDX
    -0.07
    ãĥ¥ãĥ¼
    -0.07
    alaria
    -0.06
    ijn
    -0.06
    lier
    -0.06
    ANCELED
    -0.06
    /***/
    -0.06
    /effects
    -0.06
    ripsi
    -0.06
    POSITIVE LOGITS
    abei
    0.07
    ãĥ¼ãĥª
    0.07
     mild
    0.06
    sdk
    0.06
     Convention
    0.06
    indo
    0.06
    oad
    0.06
    ilk
    0.06
     má»ģm
    0.06
    jec
    0.06
    Activations Density 0.000%

    No Known Activations