© 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. 87410
    Prev
    Next
    INDEX
    Explanations

    patterns of increasing numerical values

    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
    Ñıм
    -0.07
    zcze
    -0.07
    bens
    -0.07
    reten
    -0.07
     بÙĪابة
    -0.07
    wnd
    -0.06
    ucks
    -0.06
    yth
    -0.06
    crm
    -0.06
    ifiant
    -0.06
    POSITIVE LOGITS
    0.07
    orners
    0.06
    è³Ģ
    0.06
    ););↵
    0.06
    ograph
    0.06
    roll
    0.05
     verde
    0.05
    íĥķ
    0.05
    ãģĭãģ®
    0.05
     Chloe
    0.05
    Activations Density 0.013%

    No Known Activations