© 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. 1165
    Prev
    Next
    INDEX
    Explanations

    punctuations and section separators in the text

    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
    anes
    -0.08
    erus
    -0.07
    ius
    -0.07
    ound
    -0.07
    apyrus
    -0.06
    istrict
    -0.06
    oeff
    -0.06
    ÃŁen
    -0.06
    جاÙĨ
    -0.06
    zie
    -0.06
    POSITIVE LOGITS
    elere
    0.07
    ue
    0.06
     followed
    0.06
     another
    0.06
    ormsg
    0.06
    岸
    0.06
     second
    0.06
    Marks
    0.06
    aches
    0.06
     Marks
    0.06
    Activations Density 0.000%

    No Known Activations