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. 22-LLAMASCOPE-RES-131K
    6. 4493
    Prev
    Next
    INDEX
    Explanations

    numerical or statistical data points

    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
    951
    -0.07
     eg
    -0.06
    ibi
    -0.06
    201
    -0.06
    001
    -0.06
    ®
    -0.06
     pä
    -0.06
     Fah
    -0.06
    963
    -0.06
    eg
    -0.06
    POSITIVE LOGITS
    adiens
    0.07
    ãģªãģĹ
    0.07
     ActionTypes
    0.07
    oppel
    0.07
    ientos
    0.06
    øre
    0.06
     Rear
    0.06
    obl
    0.06
    ัà¸Ļà¸Ĺ
    0.06
     amongst
    0.06
    Activations Density 0.025%

    No Known Activations