© 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. 104409
    Prev
    Next
    INDEX
    Explanations

    elements related to time and physical attributes

    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
    former
    -0.08
    ãĤ¦ãĤ©
    -0.07
    gewater
    -0.07
     Blasio
    -0.07
    urrets
    -0.07
    engin
    -0.07
    prit
    -0.06
    phies
    -0.06
    479
    -0.06
    社
    -0.06
    POSITIVE LOGITS
     fucking
    0.07
     Bapt
    0.06
     stands
    0.06
     fuck
    0.06
     Fuck
    0.06
    stands
    0.06
     Snake
    0.06
     casual
    0.06
     Sokol
    0.06
     Fell
    0.06
    Activations Density 0.000%

    No Known Activations