© 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. 4095
    Prev
    Next
    INDEX
    Explanations

    references to non-native elements or influences in a given context

    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
    olem
    -0.08
    arkin
    -0.07
    ausible
    -0.07
    Ïģα
    -0.07
    аниÑĨ
    -0.07
    processable
    -0.07
    engin
    -0.07
    bris
    -0.07
    oš
    -0.07
     (~(
    -0.06
    POSITIVE LOGITS
     either
    0.07
     directly
    0.07
    Ìĥ
    0.06
    áty
    0.06
     actual
    0.06
     Either
    0.06
    either
    0.06
    paid
    0.06
    &↵
    0.05
    IID
    0.05
    Activations Density 0.008%

    No Known Activations