© 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. 74152
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and their dynamics

    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
    rray
    -0.09
    _mC
    -0.08
    Debe
    -0.08
    deniz
    -0.08
    _mD
    -0.08
    _Tis
    -0.08
    arf
    -0.08
    ewis
    -0.08
    SystemService
    -0.07
    幸
    -0.07
    POSITIVE LOGITS
     suddenly
    0.10
     disappear
    0.07
     die
    0.07
     sudden
    0.07
     died
    0.07
     disappeared
    0.07
     seemingly
    0.07
     become
    0.06
     Suddenly
    0.06
     disappears
    0.06
    Activations Density 0.030%

    No Known Activations