© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 126868
    Prev
    Next
    INDEX
    Explanations

    the word "on" and phrases that indicate a viewpoint or opinion

    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
    εÏį
    -0.07
    uhe
    -0.07
    <fieldset
    -0.07
    odable
    -0.07
    неÑĤ
    -0.06
    entifier
    -0.06
    .study
    -0.06
    reating
    -0.06
    xbf
    -0.06
     grounds
    -0.06
    POSITIVE LOGITS
    adi
    0.06
     Cob
    0.06
     Conn
    0.06
    ollapse
    0.06
    ª
    0.06
     Dispatcher
    0.06
    firm
    0.06
    μμ
    0.06
    ade
    0.06
     Dynam
    0.05
    Activations Density 0.010%

    No Known Activations