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. 95947
    Prev
    Next
    INDEX
    Explanations

    numerical data and specific details in structured formats

    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
    agma
    -0.07
    itz
    -0.06
    /Framework
    -0.06
    alore
    -0.06
    alen
    -0.05
    FindObject
    -0.05
     nevertheless
    -0.05
     ham
    -0.05
    alar
    -0.05
     agg
    -0.05
    POSITIVE LOGITS
    ispers
    0.07
    æīįèĥ½
    0.06
     оно
    0.06
    į¼
    0.06
     åŁ
    0.06
    Responder
    0.06
    ICAST
    0.06
    exels
    0.06
    ίλ
    0.06
    åŁĭ
    0.06
    Activations Density 0.095%

    No Known Activations