© 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. 93640
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measurements or calculations

    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
    chu
    -0.06
    lý
    -0.06
    oog
    -0.06
    asmine
    -0.06
    wise
    -0.06
    ·»
    -0.05
     ↵
    -0.05
    esse
    -0.05
     dow
    -0.05
    asc
    -0.05
    POSITIVE LOGITS
    nof
    0.07
    ATOR
    0.07
    ó
    0.07
    quete
    0.06
    udur
    0.06
    OURCE
    0.06
    oleÄį
    0.06
    Ïĥή
    0.06
    480
    0.06
    arat
    0.06
    Activations Density 0.040%

    No Known Activations