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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2221
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and commands

    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
    azzi
    -0.10
    iland
    -0.07
    orado
    -0.07
    ahat
    -0.06
    bjerg
    -0.06
    SetActive
    -0.06
    _FWD
    -0.06
    eree
    -0.06
    lia
    -0.06
    ONSE
    -0.06
    POSITIVE LOGITS
     parent
    0.15
    .parent
    0.12
     parents
    0.12
    getParent
    0.12
     Parent
    0.12
     getParent
    0.12
    parent
    0.11
     back
    0.11
    .getParent
    0.11
    _parent
    0.11
    Activations Density 0.037%

    No Known Activations