Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43692
    Prev
    Next
    INDEX
    Explanations

    mentions of specific people and names associated with various events or subjects

    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
    leshooting
    -0.07
    xbd
    -0.07
    STANCE
    -0.06
    SSIP
    -0.06
     Sabb
    -0.06
     Tradable
    -0.06
    Connell
    -0.06
    leshoot
    -0.06
    PACE
    -0.06
    Ú©Ø´
    -0.06
    POSITIVE LOGITS
    urer
    0.16
    åύ
    0.15
    orer
    0.15
    arer
    0.15
    ler
    0.14
    iler
    0.14
    rer
    0.14
    iner
    0.14
    uer
    0.14
    ater
    0.14
    Activations Density 1.198%

    No Known Activations