© 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. 9-LLAMASCOPE-RES-131K
    11. 98895
    Prev
    Next
    INDEX
    Explanations

    calls to action related to educational and community programs

    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
     spr
    -0.06
    ãĤ·ãĤ¢
    -0.06
     von
    -0.06
     Sem
    -0.05
    оги
    -0.05
     sch
    -0.05
     W
    -0.05
     D
    -0.05
     sw
    -0.05
    inc
    -0.05
    POSITIVE LOGITS
    aben
    0.09
    Fizz
    0.08
    anje
    0.08
    Įĵ
    0.08
    .MessageBox
    0.08
    gree
    0.08
    mmo
    0.08
    eyin
    0.08
     fisse
    0.08
    æ¢
    0.07
    Activations Density 0.036%

    No Known Activations