© 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. 82704
    Prev
    Next
    INDEX
    Explanations

    variations of the word "Aval" and its association with other terms

    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
    liqu
    -0.08
    lrt
    -0.07
    UpInside
    -0.07
    eling
    -0.07
    ضÙĦ
    -0.06
    ouston
    -0.06
    ÏħÏĥ
    -0.06
    ulos
    -0.06
    SizeMode
    -0.06
    ÑĨов
    -0.06
    POSITIVE LOGITS
    erra
    0.07
    lege
    0.07
    bara
    0.07
    eni
    0.06
    uate
    0.06
    릿
    0.06
    ucursal
    0.06
    atto
    0.06
    icare
    0.06
    ine
    0.06
    Activations Density 0.012%

    No Known Activations