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

    Neuronpedia

    Jacobian LensNEW
    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. 118803
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of being free from responsibility or danger

    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
    .fm
    -0.06
    anny
    -0.06
    .createFrom
    -0.06
     hotels
    -0.06
    าà¸į
    -0.06
    itories
    -0.06
    emsp
    -0.06
     ola
    -0.06
    飯åºĹ
    -0.06
     actionTypes
    -0.06
    POSITIVE LOGITS
    aks
    0.07
    egie
    0.07
    uga
    0.06
    Ñĥмов
    0.06
    xde
    0.06
    ignon
    0.06
    aga
    0.06
    lot
    0.06
     Tep
    0.06
    ãĥĥãĥģ
    0.06
    Activations Density 0.000%

    No Known Activations