© 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. 74850
    Prev
    Next
    INDEX
    Explanations

    references to email communication and confirmation

    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
    862
    -0.06
     mouth
    -0.06
    isy
    -0.06
    uc
    -0.06
    isto
    -0.06
     Mouth
    -0.05
    963
    -0.05
    ovsky
    -0.05
    rey
    -0.05
    ugin
    -0.05
    POSITIVE LOGITS
    Spacer
    0.08
    altar
    0.08
    aldo
    0.07
    received
    0.07
     received
    0.07
    rollo
    0.07
    Sent
    0.07
    침
    0.07
     Splash
    0.07
    rotch
    0.07
    Activations Density 0.002%

    No Known Activations