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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96022
    Prev
    Next
    INDEX
    Explanations

    geographic regions and their corresponding contexts

    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
    å¶
    -0.08
    orum
    -0.07
     "()
    -0.07
    agli
    -0.07
    é¾Ħ
    -0.07
    ocs
    -0.07
    eturn
    -0.06
    opher
    -0.06
    ॰
    -0.06
    гоÑĢод
    -0.06
    POSITIVE LOGITS
    815
    0.06
    tik
    0.06
    inline
    0.06
    420
    0.06
    anto
    0.06
     infr
    0.06
     vac
    0.05
    iá»ģn
    0.05
    355
    0.05
    OUS
    0.05
    Activations Density 0.001%

    No Known Activations