© 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. 71596
    Prev
    Next
    INDEX
    Explanations

    expressions of potential and achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Expressions of unlimited human potential, possibility, or capability, often in motivational or inspirational contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    piler
    -0.06
    íĤ
    -0.06
    ÙĬÙĪÙĨ
    -0.06
     Mariners
    -0.06
    æļ®
    -0.06
    éĽħ
    -0.06
     rare
    -0.06
     onFinish
    -0.06
     à¤ķब
    -0.06
    icont
    -0.06
    POSITIVE LOGITS
     possibilities
    0.15
     limits
    0.14
     limitation
    0.14
     Limits
    0.13
     limit
    0.13
     sky
    0.13
    limits
    0.13
     limitations
    0.12
    limit
    0.12
    -limit
    0.12
    Activations Density 0.059%

    No Known Activations