© 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. 78538
    Prev
    Next
    INDEX
    Explanations

    elements related to music events and reviews

    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
    eson
    -0.06
     sur
    -0.06
     conf
    -0.06
    ugin
    -0.06
    ukan
    -0.06
    ÑĥÑĢн
    -0.06
    anmar
    -0.06
     Ging
    -0.06
    ÑĴ
    -0.05
     Bol
    -0.05
    POSITIVE LOGITS
    imli
    0.07
    oria
    0.07
    iÄįka
    0.07
    amble
    0.07
     CLOCK
    0.06
    ιαÏĤ
    0.06
     kapas
    0.06
    jabi
    0.06
    iac
    0.06
    óng
    0.06
    Activations Density 0.010%

    No Known Activations