© 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. 90007
    Prev
    Next
    INDEX
    Explanations

    events related to moving or relocation

    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
    ellig
    -0.08
    ewe
    -0.07
     ><?
    -0.06
     Moor
    -0.06
    Çİ
    -0.06
    agram
    -0.06
    istrat
    -0.06
    ellen
    -0.06
     mimetype
    -0.06
    abler
    -0.06
    POSITIVE LOGITS
     accordingly
    0.09
    uco
    0.08
    ORA
    0.06
    ré
    0.06
     Chapman
    0.06
    okrat
    0.06
    {{{
    0.06
    fov
    0.06
    tra
    0.06
    Ïģα
    0.06
    Activations Density 0.038%

    No Known Activations