© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 62175
    Prev
    Next
    INDEX
    Explanations

    references to volunteer opportunities and community involvement

    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
    -minus
    -0.09
    getDisplay
    -0.07
    ITableView
    -0.07
    WithMany
    -0.07
    åĩ¡
    -0.06
    Hook
    -0.06
    åħµ
    -0.06
    pyx
    -0.06
    Hooks
    -0.06
    addons
    -0.06
    POSITIVE LOGITS
    375
    0.06
    etro
    0.06
    oder
    0.06
     assist
    0.06
     help
    0.06
     Westbrook
    0.06
    oret
    0.06
     parti
    0.06
    ÏģÏĮ
    0.06
    ola
    0.06
    Activations Density 0.010%

    No Known Activations