© 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. 128888
    Prev
    Next
    INDEX
    Explanations

    elements and their attributes in HTML code

    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
    ussen
    -0.09
    ffd
    -0.08
    ngine
    -0.07
     Hüs
    -0.07
    ahy
    -0.07
    áy
    -0.07
    âĢĮاÙĨ
    -0.07
    ï¼Ń
    -0.07
    ItemAt
    -0.07
    acia
    -0.07
    POSITIVE LOGITS
    ar
    0.07
     <
    0.06
    0.06
    0.06
    ropa
    0.06
    ince
    0.06
    inst
    0.05
    ome
    0.05
     gen
    0.05
     persuasion
    0.05
    Activations Density 0.007%

    No Known Activations