© 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 EvalsExportsAPI 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. 40371
    Prev
    Next
    INDEX
    Explanations

    color-related elements or attributes in the text

    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
    itters
    -0.08
    lef
    -0.08
    zon
    -0.07
    adena
    -0.07
    ERSHEY
    -0.06
    ISCO
    -0.06
    weit
    -0.06
     зави
    -0.06
    abez
    -0.06
    udden
    -0.06
    POSITIVE LOGITS
    edio
    0.07
    iva
    0.06
    ãģıãĤĵ
    0.06
     kicker
    0.06
    ary
    0.06
     Mag
    0.06
    red
    0.06
     gold
    0.06
    ìĥī
    0.06
     recon
    0.06
    Activations Density 0.004%

    No Known Activations