© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73839
    Prev
    Next
    INDEX
    Explanations

    references to vaccine-related side effects and complications

    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
    RowAt
    -0.08
    áy
    -0.07
    è
    -0.07
    usta
    -0.07
    resas
    -0.06
    -validate
    -0.06
    çĹħ
    -0.06
     Ñĥник
    -0.06
    767
    -0.06
    478
    -0.06
    POSITIVE LOGITS
    ocard
    0.07
    üzel
    0.07
    propri
    0.07
     menstr
    0.07
     sinc
    0.06
     vas
    0.06
     Gard
    0.06
    esel
    0.06
     hyp
    0.06
    ëĦ·
    0.06
    Activations Density 0.006%

    No Known Activations