© 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. 93289
    Prev
    Next
    INDEX
    Explanations

    programming functions related to adding, registering, or inserting elements, particularly in a data structure context

    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
    ानन
    -0.07
    -mf
    -0.07
    виÑĩай
    -0.07
    esh
    -0.07
    pring
    -0.07
    goo
    -0.07
    reich
    -0.06
    abcdefghijklmnop
    -0.06
    lobber
    -0.06
     quo
    -0.06
    POSITIVE LOGITS
     addition
    0.09
    ToAdd
    0.08
     new
    0.08
     addItem
    0.08
     addObject
    0.08
    /add
    0.08
     добав
    0.07
     ì¶Ķê°Ģ
    0.07
     item
    0.07
     adds
    0.07
    Activations Density 0.032%

    No Known Activations