© 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. 77894
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to access and infrastructure in publishing and knowledge management

    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
     McCart
    -0.07
    uco
    -0.06
    target
    -0.06
    OTP
    -0.06
     kin
    -0.06
    /target
    -0.06
    ql
    -0.06
    .activate
    -0.06
    .metro
    -0.05
    713
    -0.05
    POSITIVE LOGITS
     access
    0.08
     freely
    0.08
    AccessType
    0.08
    -public
    0.08
     Truy
    0.07
     Bilim
    0.07
    Open
    0.07
     Access
    0.07
     scientific
    0.07
    /Open
    0.07
    Activations Density 0.004%

    No Known Activations