© 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. 89869
    Prev
    Next
    INDEX
    Explanations

    high-quality image and resolution terms

    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
    èľľ
    -0.08
    ubo
    -0.07
    urette
    -0.07
     metav
    -0.07
    389
    -0.07
    @nate
    -0.07
    okino
    -0.07
    ÅĻeh
    -0.07
    kovi
    -0.07
    uraa
    -0.07
    POSITIVE LOGITS
    uele
    0.06
     Hol
    0.06
    Descriptor
    0.06
     Cru
    0.06
     quality
    0.06
    n
    0.06
     unless
    0.06
     Lam
    0.05
     factor
    0.05
    ency
    0.05
    Activations Density 0.000%

    No Known Activations