© 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. 31747
    Prev
    Next
    INDEX
    Explanations

    phrases indicating lack of access or disadvantage

    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
    ugins
    -0.06
    ylon
    -0.06
    uset
    -0.06
    goto
    -0.05
    ampilkan
    -0.05
     ober
    -0.05
    asons
    -0.05
    overe
    -0.05
    averse
    -0.05
     blah
    -0.05
    POSITIVE LOGITS
    Trou
    0.07
     safest
    0.07
    luck
    0.07
     unless
    0.07
    571
    0.07
    ikat
    0.07
     advant
    0.07
    unless
    0.06
     Unless
    0.06
    leur
    0.06
    Activations Density 0.030%

    No Known Activations