© 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. 107462
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal recognition or credentials

    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
    .opend
    -0.07
     à¤ľà¤¬à¤ķ
    -0.07
    \Doctrine
    -0.07
    ãģijãĤĮãģ©
    -0.07
    ấu
    -0.07
    .way
    -0.06
     вообÑīе
    -0.06
    añ
    -0.06
    âĸ¡
    -0.06
     eskort
    -0.06
    POSITIVE LOGITS
    :
    0.14
    :↵
    0.12
    :&
    0.09
    :-
    0.08
    :**
    0.08
     :↵
    0.08
    :.
    0.08
    :↵↵
    0.08
    :č↵
    0.08
    :</
    0.08
    Activations Density 0.099%

    No Known Activations