© 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. 15-LLAMASCOPE-RES-131K
    11. 87308
    Prev
    Next
    INDEX
    Explanations

    concepts related to separation and detachment in relationships

    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
    asi
    -0.07
     Hills
    -0.07
    leine
    -0.07
    _shapes
    -0.07
    elib
    -0.07
    462
    -0.07
    hil
    -0.07
    ertime
    -0.07
    οÏħ
    -0.07
    lems
    -0.06
    POSITIVE LOGITS
     khá»ıi
    0.10
     from
    0.09
    离
    0.07
    éĽ¢
    0.07
     apart
    0.07
     separation
    0.06
    -separated
    0.06
     ç¦
    0.06
     Disconnect
    0.06
     disconnect
    0.06
    Activations Density 0.032%

    No Known Activations