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. 22-LLAMASCOPE-RES-131K
    6. 5526
    Prev
    Next
    INDEX
    Explanations

    concepts related to resilience and the ability to adapt in changing circumstances

    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
    ä¹ĭä¸Ģ
    -0.07
    kos
    -0.07
    ãĥ¶
    -0.06
    zdy
    -0.06
    ymology
    -0.06
    pies
    -0.06
    stp
    -0.06
    าà¸ĩว
    -0.06
    _ASCII
    -0.06
    poz
    -0.06
    POSITIVE LOGITS
     ability
    0.46
     Ability
    0.36
    Ability
    0.31
     abilities
    0.30
     capability
    0.29
     able
    0.28
    èĥ½åĬĽ
    0.27
    ability
    0.25
    _ability
    0.24
     capacity
    0.23
    Activations Density 0.069%

    No Known Activations