© 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. 80923
    Prev
    Next
    INDEX
    Explanations

    statistical data related to demographics and population characteristics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    hoa
    -0.08
    REQ
    -0.08
    afs
    -0.08
    intree
    -0.08
    entifier
    -0.08
    ifter
    -0.07
    Sharper
    -0.07
    orgot
    -0.07
    gmt
    -0.07
    ãĥ³ãĥĦ
    -0.07
    POSITIVE LOGITS
     Academy
    0.06
    471
    0.06
     CD
    0.06
    Template
    0.05
     Martins
    0.05
    616
    0.05
     bum
    0.05
    sn
    0.05
     дво
    0.05
     "
    0.05
    Activations Density 0.013%

    No Known Activations