© 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. 15-LLAMASCOPE-RES-131K
    11. 1043
    Prev
    Next
    INDEX
    Explanations

    keywords and concepts related to password security and user authentication

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

    Technical terminology related to unique identifiers, naming conventions, and reserved values in programming and technical systems.

    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
    bread
    -0.07
    é¼
    -0.07
    endon
    -0.07
    entai
    -0.06
    XObject
    -0.06
    çek
    -0.06
    imedia
    -0.06
    ipo
    -0.06
    çĨ
    -0.06
    nave
    -0.06
    POSITIVE LOGITS
    |unique
    0.09
     uniqueness
    0.08
    .unique
    0.07
     unique
    0.07
    _unique
    0.07
    _UNIQUE
    0.07
    Unique
    0.07
    unique
    0.07
     cho
    0.07
     Unique
    0.07
    Activations Density 0.098%

    No Known Activations