© 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. 17-LLAMASCOPE-RES-131K
    11. 85106
    Prev
    Next
    INDEX
    Explanations

    instances of the word "edited" 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
    aid
    -0.07
    ÑģÑİ
    -0.06
     vent
    -0.06
    habit
    -0.06
    hand
    -0.06
    enk
    -0.06
    hardt
    -0.06
     Winter
    -0.05
     rat
    -0.05
     agent
    -0.05
    POSITIVE LOGITS
    bject
    0.08
    omap
    0.08
    -alist
    0.07
    uba
    0.07
    ERE
    0.07
    elu
    0.07
    ERAL
    0.07
    MBProgressHUD
    0.07
    iddi
    0.07
    .gwt
    0.07
    Activations Density 0.004%

    No Known Activations