© 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. 88462
    Prev
    Next
    INDEX
    Explanations

    instances of alerts and warnings in the text

    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
    erver
    -0.08
    ething
    -0.08
    jon
    -0.07
    ãģ°
    -0.07
    erb
    -0.07
    بد
    -0.07
    aturas
    -0.07
    lish
    -0.07
    amba
    -0.07
    ORIZONTAL
    -0.06
    POSITIVE LOGITS
    ingly
    0.12
    ness
    0.10
    ting
    0.10
    iveness
    0.10
    ing
    0.09
    -dismissible
    0.09
    ive
    0.07
    ted
    0.07
    tem
    0.07
    edly
    0.07
    Activations Density 0.005%

    No Known Activations