© 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. 126085
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptors related to personality traits and character complexity

    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
    znam
    -0.09
    hsi
    -0.09
    illow
    -0.08
    éĢģæĸĻ
    -0.08
    undy
    -0.08
    Když
    -0.08
    azzi
    -0.08
     SelectList
    -0.08
    anford
    -0.08
    -INF
    -0.08
    POSITIVE LOGITS
     Mr
    0.08
     Prof
    0.07
    lic
    0.07
     Mrs
    0.06
    NESS
    0.06
     former
    0.06
     er
    0.06
    932
    0.06
    680
    0.06
    -looking
    0.06
    Activations Density 0.023%

    No Known Activations