© 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. 76179
    Prev
    Next
    INDEX
    Explanations

    technical references related to software and programming libraries

    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
    agal
    -0.06
    1
    -0.06
    -0.06
    ↵
    -0.05
     lep
    -0.05
    an
    -0.05
    ach
    -0.05
    110
    -0.05
    licer
    -0.05
    [
    -0.05
    POSITIVE LOGITS
    ByExample
    0.08
    ä¸ĭ载次æķ°
    0.08
    ENCY
    0.08
    icontrol
    0.08
    uby
    0.07
    _ros
    0.07
    ocker
    0.07
    çĽijåIJ¬é¡µéĿ¢
    0.07
    	throws
    0.07
    éĺħ读次æķ°
    0.07
    Activations Density 0.012%

    No Known Activations