© 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 EvalsExportsinterp-engineNEWAPI 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. 120547
    Prev
    Next
    INDEX
    Explanations

    references to specific programming language frameworks or libraries

    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
    ahat
    -0.08
    PILE
    -0.07
    ardu
    -0.06
    ablish
    -0.06
    bidden
    -0.06
    assium
    -0.06
    agnostic
    -0.06
    ÂĢÂ
    -0.06
     chung
    -0.06
    ôt
    -0.06
    POSITIVE LOGITS
    _PROXY
    0.07
    MF
    0.07
     Owned
    0.07
    `='$
    0.06
    ajor
    0.06
     Sever
    0.06
    grily
    0.06
    U
    0.06
     parachute
    0.06
    -American
    0.06
    Activations Density 0.008%

    No Known Activations