© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87106
    Prev
    Next
    INDEX
    Explanations

    terms related to membership and benefits in a charitable 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
    gratis
    -0.08
     à¤ħप
    -0.07
    ίοÏĤ
    -0.07
     apar
    -0.07
    оваÑĢ
    -0.07
    лиÑĤ
    -0.07
    @protocol
    -0.07
    andin
    -0.07
    ç®Ĺ
    -0.07
    OwnProperty
    -0.07
    POSITIVE LOGITS
     future
    0.07
    contin
    0.06
     legacy
    0.06
     perpet
    0.06
     forever
    0.06
     generations
    0.06
     continue
    0.06
     dec
    0.06
     memorial
    0.06
     continuity
    0.06
    Activations Density 0.003%

    No Known Activations