© 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. 72842
    Prev
    Next
    INDEX
    Explanations

    terms related to quality and positive attributes

    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
    emiah
    -0.07
    ilig
    -0.07
    UrlParser
    -0.07
     Ulus
    -0.07
    dez
    -0.07
    ranÃŃ
    -0.07
    ông
    -0.07
    stroy
    -0.07
    asse
    -0.07
    ameleon
    -0.07
    POSITIVE LOGITS
     Kur
    0.06
    à¹Ģà¸īà¸ŀาะ
    0.06
     for
    0.06
    afil
    0.06
    祥
    0.06
    nings
    0.06
    ÑģÑĤи
    0.06
    ability
    0.05
    0.05
    471
    0.05
    Activations Density 0.051%

    No Known Activations