Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 44433
    Prev
    Next
    INDEX
    Explanations

    terms related to secure communication technologies

    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
    reeze
    -0.07
    RuntimeObject
    -0.07
     RuntimeObject
    -0.07
    owler
    -0.06
    avad
    -0.06
    Apollo
    -0.06
    ĥĿ
    -0.06
     виÑıв
    -0.06
    WebKit
    -0.06
    xico
    -0.06
    POSITIVE LOGITS
     ssh
    0.21
     SSH
    0.21
    SSH
    0.18
    ssh
    0.17
    _ssh
    0.16
     scp
    0.14
     tunnel
    0.13
     Tunnel
    0.12
     tunnels
    0.12
     SOCK
    0.11
    Activations Density 0.021%

    No Known Activations