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

    Neuronpedia

    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. 82183
    Prev
    Next
    INDEX
    Explanations

    key entities such as influential families, organizations, and companies

    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
    afort
    -0.07
    ange
    -0.07
    eren
    -0.06
    zen
    -0.06
    _SB
    -0.06
     thing
    -0.06
    ìłł
    -0.06
    sen
    -0.06
    ="--
    -0.06
     Gazette
    -0.06
    POSITIVE LOGITS
     such
    0.09
    such
    0.09
    ä¹ĭä¸Ģ
    0.09
     zoals
    0.08
    ÑĢод
    0.08
    ÏĦεί
    0.08
     seperti
    0.08
    pii
    0.07
    å¦Ĥ
    0.07
    .btnCancel
    0.07
    Activations Density 0.039%

    No Known Activations