© 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. 16038
    Prev
    Next
    INDEX
    Explanations

    elements related to transformation and improvement in various contexts

    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
    ahren
    -0.07
    ikh
    -0.07
    ons
    -0.07
    Ñģим
    -0.06
    andin
    -0.06
    larım
    -0.06
    ør
    -0.06
    ump
    -0.06
    íķĺìŀIJ
    -0.06
     Invalidate
    -0.06
    POSITIVE LOGITS
    -less
    0.07
     lack
    0.07
    ä¸įäºĨ
    0.07
    igar
    0.06
     only
    0.06
    cej
    0.06
     okay
    0.06
     Lucas
    0.06
     Bernardino
    0.06
     Tucker
    0.06
    Activations Density 0.478%

    No Known Activations