© 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. 86034
    Prev
    Next
    INDEX
    Explanations

    different geometric shapes and their specifications

    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
    باÙĨ
    -0.07
    474
    -0.06
    ows
    -0.06
    hod
    -0.06
    534
    -0.06
    360
    -0.06
    amac
    -0.06
    473
    -0.06
    idth
    -0.06
    ling
    -0.06
    POSITIVE LOGITS
    -shaped
    0.16
     shaped
    0.11
     shape
    0.11
     Shape
    0.10
    shape
    0.09
    _shape
    0.09
    /oct
    0.08
    å½¢
    0.08
    .shape
    0.08
    Shape
    0.08
    Activations Density 0.026%

    No Known Activations