© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 83356
    Prev
    Next
    INDEX
    Explanations

    domain names related to websites and internet resources

    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
    onth
    -0.07
    azi
    -0.06
    ham
    -0.06
     lick
    -0.06
    iple
    -0.06
     Katz
    -0.06
    hus
    -0.06
    cul
    -0.06
    ARRY
    -0.05
    adin
    -0.05
    POSITIVE LOGITS
    ombine
    0.08
    aktion
    0.07
    ufs
    0.07
    ckill
    0.07
    eneric
    0.07
    imulator
    0.07
    _BS
    0.07
    иÑģÑĮ
    0.07
    .Failure
    0.07
    podob
    0.07
    Activations Density 0.000%

    No Known Activations