© 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. 124554
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or reflections on daily life

    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
    oru
    -0.06
    etta
    -0.06
    achel
    -0.06
    plr
    -0.06
     Miche
    -0.06
    ìłĢ
    -0.06
    SetColor
    -0.06
    -initial
    -0.05
    initial
    -0.05
     initial
    -0.05
    POSITIVE LOGITS
     frequency
    0.14
    frequency
    0.13
     rare
    0.13
    Frequency
    0.13
     every
    0.13
     rarity
    0.13
     Frequency
    0.13
     Rare
    0.12
     frequent
    0.12
     occasional
    0.12
    Activations Density 0.047%

    No Known Activations