© 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. 124790
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to memory and its properties

    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
     Cousins
    -0.06
    atatype
    -0.06
    inan
    -0.06
    ered
    -0.06
    abet
    -0.06
    ãĥ©ãĤ¤ãĥĪ
    -0.06
    MQ
    -0.06
    eced
    -0.06
    geois
    -0.06
     pedigree
    -0.06
    POSITIVE LOGITS
    orial
    0.09
    phis
    0.08
    cached
    0.08
    endez
    0.08
    antine
    0.07
    brane
    0.07
    rán
    0.07
     Mem
    0.07
    Ñģли
    0.07
    ória
    0.07
    Activations Density 0.009%

    No Known Activations