© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 30044
    Prev
    Next
    INDEX
    Explanations

    terms related to regulations and legal disclaimers

    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
     cele
    -0.07
     seksi
    -0.07
    OAD
    -0.07
    ARGIN
    -0.07
    asper
    -0.07
    midi
    -0.07
    asma
    -0.07
    nob
    -0.06
    лаб
    -0.06
    swer
    -0.06
    POSITIVE LOGITS
    igan
    0.06
     suspension
    0.06
    rl
    0.06
    RL
    0.06
     dimin
    0.06
     USE
    0.06
    ild
    0.06
    ä»ķ
    0.06
    δη
    0.06
    .Currency
    0.05
    Activations Density 0.005%

    No Known Activations