© 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 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. 17-LLAMASCOPE-RES-131K
    11. 125605
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs indicating intentions or actions

    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
    dda
    -0.08
    #
    -0.08
    avigate
    -0.07
    avig
    -0.07
    änge
    -0.07
    afa
    -0.07
     Bios
    -0.07
    acus
    -0.07
    aos
    -0.07
    attend
    -0.06
    POSITIVE LOGITS
     determine
    0.09
     determining
    0.09
     whether
    0.09
     find
    0.08
     figure
    0.08
     determination
    0.08
     deciding
    0.07
    æĺ¯åIJ¦
    0.07
     determines
    0.07
    whether
    0.07
    Activations Density 0.023%

    No Known Activations