© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 129515
    Prev
    Next
    INDEX
    Explanations

    references to cloud-based services and management systems

    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
    heimer
    -0.06
    mailer
    -0.06
    heim
    -0.06
     Memo
    -0.06
    ÙĪÙĦÙĬ
    -0.06
    ternal
    -0.06
    Memo
    -0.06
     tangent
    -0.06
    éľ²
    -0.06
    .mb
    -0.06
    POSITIVE LOGITS
     control
    0.10
     management
    0.10
    -management
    0.09
     controls
    0.09
     manage
    0.09
    control
    0.08
    -control
    0.08
     Control
    0.08
     admin
    0.08
     MANAGEMENT
    0.08
    Activations Density 0.014%

    No Known Activations