© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16657
    Prev
    Next
    INDEX
    Explanations

    instances of the word "while."

    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
    ville
    -0.06
    edBy
    -0.06
    vl
    -0.06
    etc
    -0.06
    vb
    -0.06
     either
    -0.05
    cc
    -0.05
    \-
    -0.05
    ior
    -0.05
    iasco
    -0.05
    POSITIVE LOGITS
     certainly
    0.09
    yes
    0.08
     yes
    0.08
    may
    0.08
     there
    0.08
    s
    0.08
    )((((
    0.08
     may
    0.08
    sÃŃ
    0.08
     ìĿ´ëĬĶ
    0.07
    Activations Density 0.022%

    No Known Activations