© 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 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. 106172
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of memory and recollection

    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
    zug
    -0.06
    åIJ¾
    -0.06
    ansi
    -0.06
    åıĬãģ³
    -0.06
    ï¿
    -0.06
    inh
    -0.06
    oux
    -0.06
    idae
    -0.06
    ç§ģãģ¯
    -0.06
     addCriterion
    -0.06
    POSITIVE LOGITS
    erland
    0.06
    lx
    0.06
    edik
    0.06
     array
    0.06
     wed
    0.06
     hun
    0.06
    å´İ
    0.06
    ArrayType
    0.06
    ighet
    0.06
    aterangepicker
    0.06
    Activations Density 0.000%

    No Known Activations