© 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. 127184
    Prev
    Next
    INDEX
    Explanations

    statements of support or affirmation in a context related to education

    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
    ihan
    -0.07
    Descriptors
    -0.07
    ÑĢÑĥ
    -0.07
    ÑİÑĢ
    -0.07
    leta
    -0.06
    imen
    -0.06
    empo
    -0.06
    RL
    -0.06
    ="{!!
    -0.06
    ugas
    -0.06
    POSITIVE LOGITS
    ecut
    0.07
     einzel
    0.07
    enthal
    0.07
    ejs
    0.07
    eut
    0.07
    алеж
    0.06
     Bewert
    0.06
    egg
    0.06
    ÙĪدÛĮ
    0.06
    inely
    0.06
    Activations Density 0.000%

    No Known Activations