© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129696
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and familial 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
    vod
    -0.07
    odium
    -0.07
     SelectList
    -0.07
    инг
    -0.07
    MOTE
    -0.07
    rians
    -0.07
    .Imaging
    -0.07
    ouch
    -0.07
    adol
    -0.07
     antenn
    -0.07
    POSITIVE LOGITS
     retro
    0.06
     Eth
    0.06
     Stall
    0.05
    etak
    0.05
     inher
    0.05
     an
    0.05
     NX
    0.05
     heritage
    0.05
    Svc
    0.05
     unsus
    0.05
    Activations Density 0.034%

    No Known Activations