© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 116694
    Prev
    Next
    INDEX
    Explanations

    technical terms and function calls related to graphics rendering and session 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
    Backing
    -0.07
     reign
    -0.06
     serialVersionUID
    -0.06
    piel
    -0.06
    PointerType
    -0.06
     wirk
    -0.06
    ìŬ
    -0.06
    翼
    -0.05
    why
    -0.05
     hashCode
    -0.05
    POSITIVE LOGITS
    iqueta
    0.07
     Gallagher
    0.07
    balances
    0.06
    riba
    0.06
    /Set
    0.06
    _EQUALS
    0.06
    ÑĢив
    0.06
    .Guna
    0.06
     Joh
    0.06
    ByName
    0.06
    Activations Density 0.144%

    No Known Activations