© 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. 22-LLAMASCOPE-RES-131K
    11. 3981
    Prev
    Next
    INDEX
    Explanations

    actions related to giving or returning something

    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
    erten
    -0.06
    inand
    -0.06
    til
    -0.06
    rou
    -0.06
    SSERT
    -0.06
    odor
    -0.06
    лÑĥ
    -0.05
    aliz
    -0.05
    atak
    -0.05
     buá»Ļc
    -0.05
    POSITIVE LOGITS
     turn
    0.12
     Turn
    0.11
     turned
    0.11
    .turn
    0.11
     TURN
    0.11
    -turn
    0.10
     turning
    0.10
    (turn
    0.09
     over
    0.09
    Turn
    0.09
    Activations Density 0.004%

    No Known Activations