© 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. 3487
    Prev
    Next
    INDEX
    Explanations

    titles and nobility-related terms

    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
    iferay
    -0.08
    acades
    -0.07
    ders
    -0.07
    aled
    -0.07
    aeper
    -0.06
    ród
    -0.06
    eo
    -0.06
    allas
    -0.06
    abbo
    -0.06
    pNet
    -0.06
    POSITIVE LOGITS
     of
    0.08
    à¹ģห
    0.07
     xứ
    0.07
    ess
    0.07
    ships
    0.07
    orum
    0.07
     IID
    0.06
    esses
    0.06
    hetto
    0.06
    ëĭĺ
    0.06
    Activations Density 0.007%

    No Known Activations