© 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 EvalsExportsinterp-engineNEWAPI 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. 73712
    Prev
    Next
    INDEX
    Explanations

    phrases related to family support and educational success

    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
     still
    -0.07
    âĢ¦↵
    -0.06
    nant
    -0.06
    âĢ¦
    -0.06
     although
    -0.06
    still
    -0.06
     Still
    -0.06
     yet
    -0.06
     for
    -0.06
    åħ
    -0.06
    POSITIVE LOGITS
    aira
    0.09
    imos
    0.08
    ạc
    0.08
    isse
    0.07
    infeld
    0.07
     Raq
    0.07
    owi
    0.07
    تاÙĨ
    0.07
    ziej
    0.07
    RetVal
    0.07
    Activations Density 0.043%

    No Known Activations