© 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. 84221
    Prev
    Next
    INDEX
    Explanations

    references to social activities and events within a college 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
     /
    -0.07
     &
    -0.06
    -0.06
     presented
    -0.05
    ↵
    -0.05
     strang
    -0.05
     derived
    -0.05
     presenting
    -0.05
     d
    -0.05
     connected
    -0.05
    POSITIVE LOGITS
    ieee
    0.10
    chodu
    0.09
    ÑĢеменно
    0.09
     ApplicationException
    0.08
    $MESS
    0.08
    úc
    0.08
    abee
    0.08
    umblr
    0.08
    _MALLOC
    0.08
    ètre
    0.08
    Activations Density 0.001%

    No Known Activations