© 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. 125649
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Adele."

    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
    eyse
    -0.07
     sustained
    -0.06
    Buf
    -0.06
    led
    -0.06
    daÅŁ
    -0.06
    assa
    -0.05
    eldon
    -0.05
    ua
    -0.05
     aspect
    -0.05
    èĬ
    -0.05
    POSITIVE LOGITS
    uten
    0.07
    ék
    0.07
     incumb
    0.07
    ARB
    0.07
    peater
    0.07
    ewidth
    0.06
    enek
    0.06
    icity
    0.06
    VERRIDE
    0.06
    اض
    0.06
    Activations Density 0.001%

    No Known Activations