© 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. 5-LLAMASCOPE-RES-131K
    11. 126618
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Arrington."

    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
    ÌĪ
    -0.07
    erah
    -0.07
    ighton
    -0.07
    -0.07
    bies
    -0.06
    aday
    -0.06
    addock
    -0.06
    ouch
    -0.06
    ib
    -0.06
    ings
    -0.06
    POSITIVE LOGITS
    naire
    0.09
    nal
    0.08
    evity
    0.07
    lycer
    0.07
    opher
    0.07
    ky
    0.07
    CRM
    0.07
    shire
    0.07
    -client
    0.07
    ãĥ³
    0.07
    Activations Density 0.010%

    No Known Activations