© 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. 84379
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Omar" and other related proper nouns

    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
    kova
    -0.07
    826
    -0.07
    VENTORY
    -0.07
    ruby
    -0.06
    utenberg
    -0.06
    rus
    -0.06
    zza
    -0.06
     Kob
    -0.06
    ëĤĺ무
    -0.06
    arest
    -0.06
    POSITIVE LOGITS
    رÙĬÙĥ
    0.07
    otto
    0.07
    opia
    0.07
     cellFor
    0.07
    æ¶
    0.06
    asis
    0.06
    ivot
    0.06
    asing
    0.06
     borr
    0.06
     corre
    0.06
    Activations Density 0.010%

    No Known Activations