© 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. 117575
    Prev
    Next
    INDEX
    Explanations

    references to medical or scientific research articles and their associated metrics

    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
    thal
    -0.06
    morph
    -0.06
     xsi
    -0.06
    trys
    -0.06
    575
    -0.06
     dia
    -0.06
    athom
    -0.06
    orta
    -0.06
    iza
    -0.06
    ropa
    -0.06
    POSITIVE LOGITS
    uvre
    0.07
    assed
    0.06
    CEE
    0.06
    áfico
    0.06
    ÌĨ
    0.06
    EGIN
    0.06
    quee
    0.06
    ÙĪاÙĦ
    0.06
    gard
    0.06
     Suppress
    0.06
    Activations Density 0.017%

    No Known Activations