© 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. 60592
    Prev
    Next
    INDEX
    Explanations

    programming language constructs related to variable and type declarations

    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
    iddle
    -0.06
     al
    -0.06
    hare
    -0.05
     Args
    -0.05
     fab
    -0.05
     rat
    -0.05
     Prism
    -0.05
    privileged
    -0.05
    whereIn
    -0.05
     than
    -0.05
    POSITIVE LOGITS
    елем
    0.07
    ortex
    0.07
    ivent
    0.07
    HideInInspector
    0.07
    inux
    0.07
    .setter
    0.07
    маз
    0.07
    à¹ĩà¸Ńà¸ģ
    0.07
    жд
    0.07
    ÐĴаж
    0.07
    Activations Density 0.010%

    No Known Activations