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. 43450
    Prev
    Next
    INDEX
    Explanations

    terms related to teleportation and programming functionalities

    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
    /Area
    -0.07
    /Dk
    -0.07
     awakeFromNib
    -0.06
    _mE
    -0.06
    ramework
    -0.06
    ichte
    -0.06
    ÑĢÑĥÑĪ
    -0.06
    /Framework
    -0.06
     Shooter
    -0.06
    /MPL
    -0.06
    POSITIVE LOGITS
     operation
    0.15
     action
    0.13
     step
    0.12
     procedure
    0.12
     request
    0.12
     operations
    0.12
     routine
    0.12
     process
    0.11
     logic
    0.11
     phase
    0.11
    Activations Density 0.122%

    No Known Activations