© 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. 72467
    Prev
    Next
    INDEX
    Explanations

    temporal references indicating the present or immediate time

    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
    ais
    -0.07
    iana
    -0.07
    ango
    -0.06
    ouz
    -0.06
    ei
    -0.06
    ura
    -0.05
    arma
    -0.05
     Sle
    -0.05
    greg
    -0.05
     Wag
    -0.05
    POSITIVE LOGITS
    ümÃ¼ÅŁ
    0.08
    âĸį
    0.07
    å°
    0.07
    .UnitTesting
    0.07
    -urlencoded
    0.07
    acomment
    0.07
    _MAY
    0.07
    çek
    0.07
    orarily
    0.07
    -Mart
    0.07
    Activations Density 0.009%

    No Known Activations