© 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. 77247
    Prev
    Next
    INDEX
    Explanations

    references to individual success and achievements in various fields

    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
    seau
    -0.07
    uxe
    -0.07
    .showMessage
    -0.07
     retirees
    -0.07
    Tube
    -0.07
    tain
    -0.07
    ritel
    -0.07
    ¹æŀľ
    -0.07
    aye
    -0.06
    ình
    -0.06
    POSITIVE LOGITS
     young
    0.24
     Young
    0.20
    young
    0.20
     youngest
    0.19
     younger
    0.19
    Young
    0.18
     youthful
    0.17
     genç
    0.16
     молод
    0.15
     youth
    0.14
    Activations Density 0.072%

    No Known Activations