© 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. 31658
    Prev
    Next
    INDEX
    Explanations

    keywords related to authorship and attribution

    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
     Fun
    -0.05
    æ°
    -0.05
     Jar
    -0.05
    ito
    -0.05
     Wa
    -0.05
     SEL
    -0.05
    erosis
    -0.05
    TAG
    -0.05
    erb
    -0.05
     sel
    -0.05
    POSITIVE LOGITS
    ATUS
    0.08
    RSS
    0.07
    own
    0.07
    WWW
    0.07
    Drv
    0.07
     subur
    0.07
     вÑģп
    0.07
    dbl
    0.07
    IDGE
    0.07
    KeyValuePair
    0.07
    Activations Density 0.008%

    No Known Activations