© 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. 84276
    Prev
    Next
    INDEX
    Explanations

    recommendations and positive testimonials for a home inspector named Chris

    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
    emma
    -0.07
    elib
    -0.07
    aft
    -0.06
     Bene
    -0.06
    angu
    -0.06
    ober
    -0.06
    nem
    -0.06
    ÐĴÐŀ
    -0.06
    ÑĢез
    -0.06
    лем
    -0.06
    POSITIVE LOGITS
     anyone
    0.09
     unto
    0.09
     anybody
    0.09
     anytime
    0.08
     Anyone
    0.08
     any
    0.07
     ANY
    0.07
    ela
    0.07
    Anyone
    0.07
     rahat
    0.07
    Activations Density 0.006%

    No Known Activations