© 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. 29319
    Prev
    Next
    INDEX
    Explanations

    references to age and family relationships involving children

    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
    itra
    -0.07
    Radians
    -0.06
    dad
    -0.06
    agli
    -0.06
    oya
    -0.06
    ÅĤaw
    -0.06
    Ñıн
    -0.06
    unta
    -0.06
    juan
    -0.06
     koc
    -0.06
    POSITIVE LOGITS
    keh
    0.06
    (IB
    0.06
    .Management
    0.06
    راÙĩ
    0.06
     son
    0.06
     gord
    0.06
    preter
    0.06
     smaller
    0.06
    obus
    0.05
    çģ°
    0.05
    Activations Density 0.016%

    No Known Activations