© 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. 29164
    Prev
    Next
    INDEX
    Explanations

    references to citations and figures in academic writing

    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
    agg
    -0.07
    hausen
    -0.07
    itchens
    -0.07
    ën
    -0.07
     Zw
    -0.06
    stitial
    -0.06
    perator
    -0.06
    avan
    -0.06
    occo
    -0.06
    ubi
    -0.06
    POSITIVE LOGITS
    svc
    0.06
    rame
    0.06
    ä¹ī
    0.06
    ITA
    0.06
    اپ
    0.06
    emachine
    0.06
    еви
    0.05
     rough
    0.05
     Lambert
    0.05
    747
    0.05
    Activations Density 0.030%

    No Known Activations