© 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. 126721
    Prev
    Next
    INDEX
    Explanations

    components related to technical specifications and programming structures

    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
    ,
    -0.06
    ritch
    -0.05
    اسة
    -0.05
    AK
    -0.05
     pal
    -0.05
     Mann
    -0.05
     scape
    -0.05
     Ez
    -0.05
     Myers
    -0.05
    etz
    -0.05
    POSITIVE LOGITS
    istrovstvÃŃ
    0.11
    åı¦ä¸Ģ
    0.11
    renom
    0.08
     ostatnÃŃ
    0.08
    'autres
    0.08
    another
    0.08
     दà¤ķ
    0.07
    ãĤĤãģĨ
    0.07
    λογ
    0.07
    usercontent
    0.07
    Activations Density 0.560%

    No Known Activations