© 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. 9-LLAMASCOPE-RES-131K
    11. 97696
    Prev
    Next
    INDEX
    Explanations

    phrases related to observation and perception

    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
    alis
    -0.07
    /or
    -0.07
    IRR
    -0.06
    ÐĬ
    -0.06
    audi
    -0.06
    nten
    -0.06
    anker
    -0.06
    era
    -0.06
    EO
    -0.06
    IRROR
    -0.06
    POSITIVE LOGITS
    ograd
    0.07
    eworld
    0.06
    787
    0.06
     Rack
    0.06
     Jun
    0.06
     Coun
    0.06
    ahlen
    0.06
     Jarvis
    0.06
     attaching
    0.06
    \Queue
    0.06
    Activations Density 0.008%

    No Known Activations