© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106417
    Prev
    Next
    INDEX
    Explanations

    elements related to business and organizational structures

    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
    inel
    -0.07
    ibold
    -0.07
    \Annotation
    -0.07
    okit
    -0.07
    746
    -0.07
    ư
    -0.07
    -alist
    -0.07
    onal
    -0.07
    325
    -0.06
    tings
    -0.06
    POSITIVE LOGITS
    ENUM
    0.07
     another
    0.07
    olini
    0.07
     one
    0.06
     recently
    0.06
     maj
    0.06
    etta
    0.06
     faç
    0.06
     XX
    0.06
     multi
    0.06
    Activations Density 0.005%

    No Known Activations