© 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. 87821
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "were."

    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
     "
    -0.08
     famously
    -0.06
    renal
    -0.06
     —
    -0.06
    öl
    -0.06
    FI
    -0.06
     âĢŀ
    -0.06
     [âĢ¦]
    -0.05
     [...]
    -0.05
     ("
    -0.05
    POSITIVE LOGITS
    voj
    0.08
    panse
    0.08
    beit
    0.08
    inae
    0.07
    jeme
    0.07
    ارش
    0.07
    нки
    0.07
     compilers
    0.06
    ewis
    0.06
    artz
    0.06
    Activations Density 0.000%

    No Known Activations