© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 119799
    Prev
    Next
    INDEX
    Explanations

    academic guidelines and requirements related to writing and assignments

    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
    ŀ
    -0.07
    æ°
    -0.06
     BILL
    -0.06
    irut
    -0.06
    gest
    -0.06
     speaker
    -0.06
    agem
    -0.06
    جر
    -0.05
    áºŃu
    -0.05
     billing
    -0.05
    POSITIVE LOGITS
     marks
    0.09
     Marks
    0.08
    Marks
    0.08
     essay
    0.08
     exam
    0.07
    marks
    0.07
     ìłľì¶ľ
    0.07
    CreateTime
    0.07
     Euras
    0.07
    -answer
    0.07
    Activations Density 0.092%

    No Known Activations