© 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. 87370
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to quality and customer service

    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
    717
    -0.07
     Dut
    -0.06
    ies
    -0.06
    ì
    -0.06
    usan
    -0.06
    bern
    -0.06
    iegel
    -0.06
     oneself
    -0.06
    asm
    -0.06
    ij
    -0.06
    POSITIVE LOGITS
    oreach
    0.09
    ifr
    0.08
     your
    0.08
    rchive
    0.07
     YOUR
    0.07
    LOPT
    0.07
    hci
    0.07
    lient
    0.07
    ãĥ¼ãĥĨ
    0.07
    dbg
    0.07
    Activations Density 0.026%

    No Known Activations