Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 57437
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to "ke" or similar variations

    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
    dart
    -0.07
    orro
    -0.07
    sure
    -0.07
    yro
    -0.07
    ipur
    -0.07
    opies
    -0.07
    åĭ
    -0.07
    isin
    -0.07
    xor
    -0.06
    adle
    -0.06
    POSITIVE LOGITS
    stad
    0.07
    pedia
    0.06
     surround
    0.06
    efe
    0.06
    pile
    0.06
    ith
    0.06
     Kraj
    0.06
    psc
    0.06
     superintendent
    0.06
    bulan
    0.06
    Activations Density 0.015%

    No Known Activations