© 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. 17-LLAMASCOPE-RES-131K
    11. 56920
    Prev
    Next
    INDEX
    Explanations

    phrases indicating achievement or becoming a particular type of person or entity, often in a motivational context

    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
    ãĥ¼ãĤ¹
    -0.07
    Å¡t
    -0.06
     Hell
    -0.06
    kd
    -0.06
     hell
    -0.06
    ilt
    -0.06
     Tam
    -0.06
    lando
    -0.06
     iota
    -0.06
    áf
    -0.05
    POSITIVE LOGITS
    inh
    0.07
    ·æĸ°
    0.07
    avor
    0.07
    reeze
    0.07
    aller
    0.07
    ovo
    0.06
    amo
    0.06
    ropp
    0.06
     Hava
    0.06
    aml
    0.06
    Activations Density 0.011%

    No Known Activations