© 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. 107574
    Prev
    Next
    INDEX
    Explanations

    phrases, quotes, and specific keywords or special characters related to search operations

    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
    ãĥĶãĥ¼
    -0.09
    atics
    -0.09
    Globals
    -0.08
    anik
    -0.07
    planation
    -0.07
    _NOP
    -0.07
    oundation
    -0.07
    iasm
    -0.07
     neutr
    -0.07
    erras
    -0.07
    POSITIVE LOGITS
    å±±å¸Ĥ
    0.08
     great
    0.07
    å·ŀå¸Ĥ
    0.07
    ecz
    0.07
     Golden
    0.07
     golden
    0.06
     Great
    0.06
    uddy
    0.06
    onte
    0.06
    olumn
    0.06
    Activations Density 0.069%

    No Known Activations