© 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. 9-LLAMASCOPE-RES-131K
    11. 97054
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface scripts and components

    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
    kh
    -0.06
    urg
    -0.06
    اÙĪÛĮ
    -0.06
    ãĥķãĤ§
    -0.06
    ãĥ¼ãĥ«
    -0.06
    utan
    -0.06
    vig
    -0.06
     premise
    -0.06
    kie
    -0.06
    priv
    -0.05
    POSITIVE LOGITS
    arrant
    0.08
    istrovstvÃŃ
    0.07
    olar
    0.06
    SizePolicy
    0.06
    igs
    0.06
     ì²ľ
    0.06
    akter
    0.06
    اÛĮد
    0.06
    ozÃŃ
    0.06
    821
    0.06
    Activations Density 0.152%

    No Known Activations