© 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. 116337
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the act of having

    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
    anime
    -0.08
    elves
    -0.07
    _trace
    -0.07
    æij©
    -0.07
    que
    -0.07
    ott
    -0.07
    alars
    -0.07
    vla
    -0.07
    nej
    -0.07
    chef
    -0.07
    POSITIVE LOGITS
     fun
    0.08
    aways
    0.06
    uters
    0.06
    lak
    0.06
    ç«¥
    0.06
     ord
    0.06
    pus
    0.05
    lland
    0.05
     Fun
    0.05
    _preferences
    0.05
    Activations Density 0.014%

    No Known Activations