© 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. 129458
    Prev
    Next
    INDEX
    Explanations

    phrases related to making selections or choices

    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
    endar
    -0.06
    resh
    -0.06
     Dans
    -0.06
    aps
    -0.06
     unfair
    -0.06
    ductor
    -0.06
    essor
    -0.06
    ietf
    -0.06
    anager
    -0.05
    ald
    -0.05
    POSITIVE LOGITS
    APON
    0.08
    'gc
    0.07
    egie
    0.07
    ViewById
    0.07
     desired
    0.07
    .newArrayList
    0.07
    vanished
    0.07
    /select
    0.06
    desired
    0.06
     LSM
    0.06
    Activations Density 0.005%

    No Known Activations