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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 26645
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and family 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
    ģn
    -0.08
    anggan
    -0.08
    rong
    -0.08
    BILE
    -0.08
    ypad
    -0.08
    ÅĽnie
    -0.08
    åijĬ
    -0.07
    meric
    -0.07
    exus
    -0.07
    ervers
    -0.07
    POSITIVE LOGITS
     Sam
    0.07
     Parr
    0.07
     hi
    0.06
     Hi
    0.06
     Nar
    0.06
     leaf
    0.06
    UnderTest
    0.06
     Broad
    0.05
     Concurrent
    0.05
    eman
    0.05
    Activations Density 0.006%

    No Known Activations