© 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. 18353
    Prev
    Next
    INDEX
    Explanations

    verbs associated with reporting, construction, and recognition in various contexts

    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
     Birch
    -0.07
    664
    -0.06
     outs
    -0.06
    air
    -0.06
     Fior
    -0.06
    bilt
    -0.06
     lev
    -0.05
    248
    -0.05
    icl
    -0.05
     F
    -0.05
    POSITIVE LOGITS
    AndGet
    0.08
    éro
    0.07
    âĸĪâĸĪ
    0.07
    èĬ³
    0.07
    annya
    0.07
    ì´Į
    0.07
    amak
    0.07
    raç
    0.07
    ató
    0.07
    jev
    0.07
    Activations Density 0.049%

    No Known Activations