© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 63091
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sent" in various contexts, indicating communication or transmission

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    adius
    -0.07
    ustralian
    -0.07
    spor
    -0.06
    usp
    -0.06
     consensus
    -0.06
    ly
    -0.06
    ypass
    -0.06
    uds
    -0.06
    dom
    -0.06
    quat
    -0.06
    POSITIVE LOGITS
    entious
    0.11
    inel
    0.11
    recv
    0.09
     forth
    0.09
    DlgItem
    0.08
    atori
    0.08
    aphore
    0.08
    iment
    0.08
    UFFIX
    0.08
    ENCED
    0.07
    Activations Density 0.022%

    No Known Activations