© 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. 54456
    Prev
    Next
    INDEX
    Explanations

    technical terms and data structures in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Names, identifiers, or specific details of objects, entities, or concepts that are central to the document's context, such as file paths, variables, data types, locations, or specialized terminology relevant to the domain being discussed.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    .scalablytyped
    -0.09
    ¶ģ
    -0.09
    «ĺ
    -0.08
    	TokenName
    -0.08
    ngth
    -0.08
     TMPro
    -0.07
    ¯¼
    -0.07
    bstract
    -0.07
     odbor
    -0.07
    ozem
    -0.07
    POSITIVE LOGITS
    ASURE
    0.06
     rừng
    0.06
    Ậ
    0.06
     provoz
    0.06
     disastr
    0.06
    Ư
    0.06
     cháy
    0.06
    ANGED
    0.06
    Lorem
    0.06
    Į¨
    0.06
    Activations Density 19.138%

    No Known Activations