© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61828
    Prev
    Next
    INDEX
    Explanations

    phrases indicating being overwhelmed or absorbed in a situation

    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
    átka
    -0.08
    ekler
    -0.07
    lis
    -0.07
    ÑĢок
    -0.07
    ạ
    -0.06
     Mobil
    -0.06
    para
    -0.06
    atur
    -0.06
    ikk
    -0.06
    γÏĩ
    -0.06
    POSITIVE LOGITS
     Credential
    0.08
    wind
    0.08
    ÑĢави
    0.07
    .qt
    0.07
    vang
    0.07
    .gnu
    0.07
    otine
    0.06
    íĴ
    0.06
    Credential
    0.06
    UND
    0.06
    Activations Density 0.006%

    No Known Activations