© 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. 125654
    Prev
    Next
    INDEX
    Explanations

    phrases related to services and their effectiveness

    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
    ductive
    -0.06
    aris
    -0.06
    Ìģ
    -0.06
    ale
    -0.06
    grid
    -0.06
    iki
    -0.06
    656
    -0.06
    ign
    -0.06
     alike
    -0.06
    gars
    -0.06
    POSITIVE LOGITS
    евиÑĩ
    0.07
    .statistics
    0.07
    ãĤĵãģ©
    0.07
     ('\
    0.07
    ovich
    0.07
    WER
    0.07
    овиÑĩ
    0.07
    _Begin
    0.07
    _Find
    0.07
     Dün
    0.07
    Activations Density 0.008%

    No Known Activations