© 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. 30325
    Prev
    Next
    INDEX
    Explanations

    categories and sections relevant to news and politics

    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
    âĢ¦↵
    -0.06
    acht
    -0.06
     Standing
    -0.06
    ...↵
    -0.06
    uria
    -0.06
     Stern
    -0.05
     one
    -0.05
    cznie
    -0.05
    707
    -0.05
    islav
    -0.05
    POSITIVE LOGITS
    ç½
    0.08
    adolu
    0.08
    ToPoint
    0.07
    fea
    0.07
     Lifestyle
    0.07
    haps
    0.07
    ãĥĭãĥ¥
    0.07
    ovky
    0.07
    uitka
    0.07
    _tid
    0.07
    Activations Density 0.013%

    No Known Activations